diff options
Diffstat (limited to 'include')
87 files changed, 1256 insertions, 412 deletions
diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 8cf7e98a2c7b..9d650476d5dc 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -225,6 +225,7 @@ struct acpi_processor_errata { } piix4; }; +extern void acpi_processor_load_module(struct acpi_processor *pr); extern int acpi_processor_preregister_performance(struct acpi_processor_performance __percpu *performance); diff --git a/include/asm-generic/io-64-nonatomic-hi-lo.h b/include/asm-generic/io-64-nonatomic-hi-lo.h new file mode 100644 index 000000000000..a6806a94250d --- /dev/null +++ b/include/asm-generic/io-64-nonatomic-hi-lo.h @@ -0,0 +1,28 @@ +#ifndef _ASM_IO_64_NONATOMIC_HI_LO_H_ +#define _ASM_IO_64_NONATOMIC_HI_LO_H_ + +#include <linux/io.h> +#include <asm-generic/int-ll64.h> + +#ifndef readq +static inline __u64 readq(const volatile void __iomem *addr) +{ + const volatile u32 __iomem *p = addr; + u32 low, high; + + high = readl(p + 1); + low = readl(p); + + return low + ((u64)high << 32); +} +#endif + +#ifndef writeq +static inline void writeq(__u64 val, volatile void __iomem *addr) +{ + writel(val >> 32, addr + 4); + writel(val, addr); +} +#endif + +#endif /* _ASM_IO_64_NONATOMIC_HI_LO_H_ */ diff --git a/include/asm-generic/io-64-nonatomic-lo-hi.h b/include/asm-generic/io-64-nonatomic-lo-hi.h new file mode 100644 index 000000000000..ca546b1ff8b5 --- /dev/null +++ b/include/asm-generic/io-64-nonatomic-lo-hi.h @@ -0,0 +1,28 @@ +#ifndef _ASM_IO_64_NONATOMIC_LO_HI_H_ +#define _ASM_IO_64_NONATOMIC_LO_HI_H_ + +#include <linux/io.h> +#include <asm-generic/int-ll64.h> + +#ifndef readq +static inline __u64 readq(const volatile void __iomem *addr) +{ + const volatile u32 __iomem *p = addr; + u32 low, high; + + low = readl(p); + high = readl(p + 1); + + return low + ((u64)high << 32); +} +#endif + +#ifndef writeq +static inline void writeq(__u64 val, volatile void __iomem *addr) +{ + writel(val, addr); + writel(val >> 32, addr + 4); +} +#endif + +#endif /* _ASM_IO_64_NONATOMIC_LO_HI_H_ */ diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h index 8a3d4fde2604..6afd7d6a9899 100644 --- a/include/asm-generic/iomap.h +++ b/include/asm-generic/iomap.h @@ -70,7 +70,7 @@ extern void ioport_unmap(void __iomem *); /* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */ struct pci_dev; extern void pci_iounmap(struct pci_dev *dev, void __iomem *); -#else +#elif defined(CONFIG_GENERIC_IOMAP) struct pci_dev; static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) { } diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h index e58fcf891370..ce37349860fe 100644 --- a/include/asm-generic/pci_iomap.h +++ b/include/asm-generic/pci_iomap.h @@ -25,7 +25,7 @@ extern void __iomem *__pci_ioport_map(struct pci_dev *dev, unsigned long port, #define __pci_ioport_map(dev, port, nr) ioport_map((port), (nr)) #endif -#else +#elif defined(CONFIG_GENERIC_PCI_IOMAP) static inline void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max) { return NULL; diff --git a/include/asm-generic/poll.h b/include/asm-generic/poll.h index 44bce836d350..9ce7f44aebd2 100644 --- a/include/asm-generic/poll.h +++ b/include/asm-generic/poll.h @@ -28,6 +28,8 @@ #define POLLRDHUP 0x2000 #endif +#define POLLFREE 0x4000 /* currently only for epoll */ + struct pollfd { int fd; short events; diff --git a/include/drm/Kbuild b/include/drm/Kbuild index a5c0e10fd47d..1e38a19d68f6 100644 --- a/include/drm/Kbuild +++ b/include/drm/Kbuild @@ -2,6 +2,7 @@ header-y += drm.h header-y += drm_fourcc.h header-y += drm_mode.h header-y += drm_sarea.h +header-y += exynos_drm.h header-y += i810_drm.h header-y += i915_drm.h header-y += mga_drm.h diff --git a/include/drm/exynos_drm.h b/include/drm/exynos_drm.h index 5e120f1c5cd9..1ed3aae893a5 100644 --- a/include/drm/exynos_drm.h +++ b/include/drm/exynos_drm.h @@ -97,15 +97,30 @@ struct drm_exynos_plane_set_zpos { #define DRM_IOCTL_EXYNOS_PLANE_SET_ZPOS DRM_IOWR(DRM_COMMAND_BASE + \ DRM_EXYNOS_PLANE_SET_ZPOS, struct drm_exynos_plane_set_zpos) +#ifdef __KERNEL__ + /** - * Platform Specific Structure for DRM based FIMD. + * A structure for lcd panel information. * * @timing: default video mode for initializing + * @width_mm: physical size of lcd width. + * @height_mm: physical size of lcd height. + */ +struct exynos_drm_panel_info { + struct fb_videomode timing; + u32 width_mm; + u32 height_mm; +}; + +/** + * Platform Specific Structure for DRM based FIMD. + * + * @panel: default panel info for initializing * @default_win: default window layer number to be used for UI. * @bpp: default bit per pixel. */ struct exynos_drm_fimd_pdata { - struct fb_videomode timing; + struct exynos_drm_panel_info panel; u32 vidcon0; u32 vidcon1; unsigned int default_win; @@ -139,4 +154,5 @@ struct exynos_drm_hdmi_pdata { unsigned int bpp; }; -#endif +#endif /* __KERNEL__ */ +#endif /* _EXYNOS_DRM_H_ */ diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h index 514ed45c462e..d117b29d1062 100644 --- a/include/linux/amba/serial.h +++ b/include/linux/amba/serial.h @@ -23,6 +23,8 @@ #ifndef ASM_ARM_HARDWARE_SERIAL_AMBA_H #define ASM_ARM_HARDWARE_SERIAL_AMBA_H +#include <linux/types.h> + /* ------------------------------------------------------------------------------- * From AMBA UART (PL010) Block Specification * ------------------------------------------------------------------------------- diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 3c1063acb2ab..94300fe46cce 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -56,6 +56,26 @@ static inline unsigned long hweight_long(unsigned long w) } /** + * rol64 - rotate a 64-bit value left + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u64 rol64(__u64 word, unsigned int shift) +{ + return (word << shift) | (word >> (64 - shift)); +} + +/** + * ror64 - rotate a 64-bit value right + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u64 ror64(__u64 word, unsigned int shift) +{ + return (word >> shift) | (word << (64 - shift)); +} + +/** * rol32 - rotate a 32-bit value left * @word: value to rotate * @shift: bits to roll diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6c6a1f008065..606cf339bb56 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -399,9 +399,6 @@ struct request_queue { /* Throttle data */ struct throtl_data *td; #endif -#ifdef CONFIG_LOCKDEP - int ioc_release_depth; -#endif }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 35eae4b67503..7c48029dffe6 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -952,7 +952,8 @@ struct cdrom_device_info { char name[20]; /* name of the device type */ /* per-device flags */ __u8 sanyo_slot : 2; /* Sanyo 3 CD changer support */ - __u8 reserved : 6; /* not used yet */ + __u8 keeplocked : 1; /* CDROM_LOCKDOOR status */ + __u8 reserved : 5; /* not used yet */ int cdda_method; /* see flags */ __u8 last_sense; __u8 media_written; /* dirty flag, DVD+RW bookkeeping */ diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 081147da0564..fbe89e17124e 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -319,13 +319,6 @@ static inline void __clocksource_updatefreq_khz(struct clocksource *cs, u32 khz) __clocksource_updatefreq_scale(cs, 1000, khz); } -static inline void -clocksource_calc_mult_shift(struct clocksource *cs, u32 freq, u32 minsec) -{ - return clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, - NSEC_PER_SEC, minsec); -} - #ifdef CONFIG_GENERIC_TIME_VSYSCALL extern void update_vsyscall(struct timespec *ts, struct timespec *wtm, diff --git a/include/linux/compat.h b/include/linux/compat.h index 41c9f6515f46..7e05fcee75a1 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -561,5 +561,9 @@ asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid, unsigned long liovcnt, const struct compat_iovec __user *rvec, unsigned long riovcnt, unsigned long flags); +#else + +#define is_compat_task() (0) + #endif /* CONFIG_COMPAT */ #endif /* _LINUX_COMPAT_H */ diff --git a/include/linux/connector.h b/include/linux/connector.h index 3c9c54fd5690..76384074262d 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -43,6 +43,7 @@ #define CN_IDX_DRBD 0x8 #define CN_VAL_DRBD 0x1 #define CN_KVP_IDX 0x9 /* HyperV KVP */ +#define CN_KVP_VAL 0x1 /* queries from the kernel */ #define CN_NETLINK_USERS 10 /* Highest index + 1 */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 1f6587590a1a..6e53b4823d7f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -44,6 +44,13 @@ extern ssize_t arch_cpu_release(const char *, size_t); #endif struct notifier_block; +#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE +extern int arch_cpu_uevent(struct device *dev, struct kobj_uevent_env *env); +extern ssize_t arch_print_cpu_modalias(struct device *dev, + struct device_attribute *attr, + char *bufptr); +#endif + /* * CPU notifier priorities. */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d64a55b23afd..ff5f5256d175 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -47,27 +47,6 @@ struct dentry_stat_t { }; extern struct dentry_stat_t dentry_stat; -/* - * Compare 2 name strings, return 0 if they match, otherwise non-zero. - * The strings are both count bytes long, and count is non-zero. - */ -static inline int dentry_cmp(const unsigned char *cs, size_t scount, - const unsigned char *ct, size_t tcount) -{ - int ret; - if (scount != tcount) - return 1; - do { - ret = (*cs != *ct); - if (ret) - break; - cs++; - ct++; - tcount--; - } while (tcount); - return ret; -} - /* Name hashing routines. Initial hash value */ /* Hash courtesy of the R5 hash in reiserfs modulo sign bits */ #define init_name_hash() 0 @@ -89,14 +68,7 @@ static inline unsigned long end_name_hash(unsigned long hash) } /* Compute the hash for a name string. */ -static inline unsigned int -full_name_hash(const unsigned char *name, unsigned int len) -{ - unsigned long hash = init_name_hash(); - while (len--) - hash = partial_name_hash(*name++, hash); - return end_name_hash(hash); -} +extern unsigned int full_name_hash(const unsigned char *, unsigned int); /* * Try to keep struct dentry aligned on 64 byte cachelines (this will @@ -309,7 +281,8 @@ extern struct dentry *d_ancestor(struct dentry *, struct dentry *); extern struct dentry *d_lookup(struct dentry *, struct qstr *); extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); extern struct dentry *__d_lookup(struct dentry *, struct qstr *); -extern struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name, +extern struct dentry *__d_lookup_rcu(const struct dentry *parent, + const struct qstr *name, unsigned *seq, struct inode **inode); /** diff --git a/include/linux/device.h b/include/linux/device.h index b63fb393aa58..f62e21689fdd 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -238,8 +238,6 @@ struct device_driver { extern int __must_check driver_register(struct device_driver *drv); extern void driver_unregister(struct device_driver *drv); -extern struct device_driver *get_driver(struct device_driver *drv); -extern void put_driver(struct device_driver *drv); extern struct device_driver *driver_find(const char *name, struct bus_type *bus); extern int driver_probe_done(void); @@ -946,14 +944,14 @@ int _dev_info(const struct device *dev, const char *fmt, ...) #define dev_info(dev, fmt, arg...) _dev_info(dev, fmt, ##arg) -#if defined(DEBUG) -#define dev_dbg(dev, format, arg...) \ - dev_printk(KERN_DEBUG, dev, format, ##arg) -#elif defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) #define dev_dbg(dev, format, ...) \ do { \ dynamic_dev_dbg(dev, format, ##__VA_ARGS__); \ } while (0) +#elif defined(DEBUG) +#define dev_dbg(dev, format, arg...) \ + dev_printk(KERN_DEBUG, dev, format, ##arg) #else #define dev_dbg(dev, format, arg...) \ ({ \ diff --git a/include/linux/digsig.h b/include/linux/digsig.h index b01558b15814..6f85a070bb45 100644 --- a/include/linux/digsig.h +++ b/include/linux/digsig.h @@ -30,7 +30,7 @@ enum digest_algo { struct pubkey_hdr { uint8_t version; /* key format version */ - time_t timestamp; /* key made, always 0 for now */ + uint32_t timestamp; /* key made, always 0 for now */ uint8_t algo; uint8_t nmpi; char mpi[0]; @@ -38,7 +38,7 @@ struct pubkey_hdr { struct signature_hdr { uint8_t version; /* signature format version */ - time_t timestamp; /* signature made */ + uint32_t timestamp; /* signature made */ uint8_t algo; uint8_t hash; uint8_t keyid[8]; diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 0564e3c39882..7e3c53a900d8 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -15,20 +15,24 @@ struct _ddebug { const char *function; const char *filename; const char *format; - unsigned int lineno:24; + unsigned int lineno:18; /* * The flags field controls the behaviour at the callsite. * The bits here are changed dynamically when the user * writes commands to <debugfs>/dynamic_debug/control */ -#define _DPRINTK_FLAGS_PRINT (1<<0) /* printk() a message using the format */ +#define _DPRINTK_FLAGS_NONE 0 +#define _DPRINTK_FLAGS_PRINT (1<<0) /* printk() a message using the format */ #define _DPRINTK_FLAGS_INCL_MODNAME (1<<1) #define _DPRINTK_FLAGS_INCL_FUNCNAME (1<<2) #define _DPRINTK_FLAGS_INCL_LINENO (1<<3) #define _DPRINTK_FLAGS_INCL_TID (1<<4) +#if defined DEBUG +#define _DPRINTK_FLAGS_DEFAULT _DPRINTK_FLAGS_PRINT +#else #define _DPRINTK_FLAGS_DEFAULT 0 +#endif unsigned int flags:8; - char enabled; } __attribute__((aligned(8))); @@ -62,21 +66,20 @@ int __dynamic_netdev_dbg(struct _ddebug *descriptor, .format = (fmt), \ .lineno = __LINE__, \ .flags = _DPRINTK_FLAGS_DEFAULT, \ - .enabled = false, \ } #define dynamic_pr_debug(fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ - if (unlikely(descriptor.enabled)) \ + if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \ __dynamic_pr_debug(&descriptor, pr_fmt(fmt), \ ##__VA_ARGS__); \ } while (0) #define dynamic_dev_dbg(dev, fmt, ...) \ do { \ - DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ - if (unlikely(descriptor.enabled)) \ + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ + if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \ __dynamic_dev_dbg(&descriptor, dev, fmt, \ ##__VA_ARGS__); \ } while (0) @@ -84,7 +87,7 @@ do { \ #define dynamic_netdev_dbg(dev, fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ - if (unlikely(descriptor.enabled)) \ + if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \ __dynamic_netdev_dbg(&descriptor, dev, fmt, \ ##__VA_ARGS__); \ } while (0) diff --git a/include/linux/elevator.h b/include/linux/elevator.h index c24f3d7fbf1e..7d4e0356f329 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -42,12 +42,6 @@ struct elevator_ops elevator_merged_fn *elevator_merged_fn; elevator_merge_req_fn *elevator_merge_req_fn; elevator_allow_merge_fn *elevator_allow_merge_fn; - - /* - * Used for both plugged list and elevator merging and in the - * former case called without queue_lock. Read comment on top of - * attempt_plug_merge() for details. - */ elevator_bio_merged_fn *elevator_bio_merged_fn; elevator_dispatch_fn *elevator_dispatch_fn; @@ -122,7 +116,6 @@ extern void elv_dispatch_add_tail(struct request_queue *, struct request *); extern void elv_add_request(struct request_queue *, struct request *, int); extern void __elv_add_request(struct request_queue *, struct request *, int); extern int elv_merge(struct request_queue *, struct request **, struct bio *); -extern int elv_try_merge(struct request *, struct bio *); extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); extern void elv_merged_request(struct request_queue *, struct request *, int); @@ -155,7 +148,7 @@ extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t); extern int elevator_init(struct request_queue *, char *); extern void elevator_exit(struct elevator_queue *); extern int elevator_change(struct request_queue *, const char *); -extern int elv_rq_merge_ok(struct request *, struct bio *); +extern bool elv_rq_merge_ok(struct request *, struct bio *); /* * Helper functions. diff --git a/include/linux/errno.h b/include/linux/errno.h index 46685832ed99..2d09bfa5c262 100644 --- a/include/linux/errno.h +++ b/include/linux/errno.h @@ -16,6 +16,7 @@ #define ERESTARTNOHAND 514 /* restart if no handler.. */ #define ENOIOCTLCMD 515 /* No ioctl command */ #define ERESTART_RESTARTBLOCK 516 /* restart by calling sys_restart_syscall */ +#define EPROBE_DEFER 517 /* Driver requests probe retry */ /* Defined for the NFSv3 protocol */ #define EBADHANDLE 521 /* Illegal NFS file handle */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 386da09f229d..69cd5bb640f5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2496,6 +2496,7 @@ extern void get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); +extern struct super_block *get_super_thawed(struct block_device *); extern struct super_block *get_active_super(struct block_device *bdev); extern void drop_super(struct super_block *sb); extern void iterate_supers(void (*)(struct super_block *, void *), void *); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 028e26f0bf08..72a6cabb4d5b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -31,16 +31,33 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); +/* + * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are + * set in the flags member. + * + * ENABLED - set/unset when ftrace_ops is registered/unregistered + * GLOBAL - set manualy by ftrace_ops user to denote the ftrace_ops + * is part of the global tracers sharing the same filter + * via set_ftrace_* debugfs files. + * DYNAMIC - set when ftrace_ops is registered to denote dynamically + * allocated ftrace_ops which need special care + * CONTROL - set manualy by ftrace_ops user to denote the ftrace_ops + * could be controled by following calls: + * ftrace_function_local_enable + * ftrace_function_local_disable + */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, FTRACE_OPS_FL_GLOBAL = 1 << 1, FTRACE_OPS_FL_DYNAMIC = 1 << 2, + FTRACE_OPS_FL_CONTROL = 1 << 3, }; struct ftrace_ops { ftrace_func_t func; struct ftrace_ops *next; unsigned long flags; + int __percpu *disabled; #ifdef CONFIG_DYNAMIC_FTRACE struct ftrace_hash *notrace_hash; struct ftrace_hash *filter_hash; @@ -97,6 +114,55 @@ int register_ftrace_function(struct ftrace_ops *ops); int unregister_ftrace_function(struct ftrace_ops *ops); void clear_ftrace_function(void); +/** + * ftrace_function_local_enable - enable controlled ftrace_ops on current cpu + * + * This function enables tracing on current cpu by decreasing + * the per cpu control variable. + * It must be called with preemption disabled and only on ftrace_ops + * registered with FTRACE_OPS_FL_CONTROL. If called without preemption + * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled. + */ +static inline void ftrace_function_local_enable(struct ftrace_ops *ops) +{ + if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL))) + return; + + (*this_cpu_ptr(ops->disabled))--; +} + +/** + * ftrace_function_local_disable - enable controlled ftrace_ops on current cpu + * + * This function enables tracing on current cpu by decreasing + * the per cpu control variable. + * It must be called with preemption disabled and only on ftrace_ops + * registered with FTRACE_OPS_FL_CONTROL. If called without preemption + * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled. + */ +static inline void ftrace_function_local_disable(struct ftrace_ops *ops) +{ + if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL))) + return; + + (*this_cpu_ptr(ops->disabled))++; +} + +/** + * ftrace_function_local_disabled - returns ftrace_ops disabled value + * on current cpu + * + * This function returns value of ftrace_ops::disabled on current cpu. + * It must be called with preemption disabled and only on ftrace_ops + * registered with FTRACE_OPS_FL_CONTROL. If called without preemption + * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled. + */ +static inline int ftrace_function_local_disabled(struct ftrace_ops *ops) +{ + WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)); + return *this_cpu_ptr(ops->disabled); +} + extern void ftrace_stub(unsigned long a0, unsigned long a1); #else /* !CONFIG_FUNCTION_TRACER */ @@ -178,12 +244,13 @@ struct dyn_ftrace { }; int ftrace_force_update(void); -void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, +int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset); -void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, +int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, int len, int reset); void ftrace_set_global_filter(unsigned char *buf, int len, int reset); void ftrace_set_global_notrace(unsigned char *buf, int len, int reset); +void ftrace_free_filter(struct ftrace_ops *ops); int register_ftrace_command(struct ftrace_func_command *cmd); int unregister_ftrace_command(struct ftrace_func_command *cmd); @@ -314,9 +381,6 @@ extern void ftrace_enable_daemon(void); #else static inline int skip_trace(unsigned long ip) { return 0; } static inline int ftrace_force_update(void) { return 0; } -static inline void ftrace_set_filter(unsigned char *buf, int len, int reset) -{ -} static inline void ftrace_disable_daemon(void) { } static inline void ftrace_enable_daemon(void) { } static inline void ftrace_release_mod(struct module *mod) {} @@ -340,6 +404,9 @@ static inline int ftrace_text_reserved(void *start, void *end) */ #define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; }) #define ftrace_set_early_filter(ops, buf, enable) do { } while (0) +#define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; }) +#define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; }) +#define ftrace_free_filter(ops) do { } while (0) static inline ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { return -ENODEV; } diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index c3da42dd22ba..dd478fc8f9f5 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -146,6 +146,10 @@ enum trace_reg { TRACE_REG_UNREGISTER, TRACE_REG_PERF_REGISTER, TRACE_REG_PERF_UNREGISTER, + TRACE_REG_PERF_OPEN, + TRACE_REG_PERF_CLOSE, + TRACE_REG_PERF_ADD, + TRACE_REG_PERF_DEL, }; struct ftrace_event_call; @@ -157,7 +161,7 @@ struct ftrace_event_class { void *perf_probe; #endif int (*reg)(struct ftrace_event_call *event, - enum trace_reg type); + enum trace_reg type, void *data); int (*define_fields)(struct ftrace_event_call *); struct list_head *(*get_fields)(struct ftrace_event_call *); struct list_head fields; @@ -165,7 +169,7 @@ struct ftrace_event_class { }; extern int ftrace_event_reg(struct ftrace_event_call *event, - enum trace_reg type); + enum trace_reg type, void *data); enum { TRACE_EVENT_FL_ENABLED_BIT, @@ -241,6 +245,7 @@ enum { FILTER_STATIC_STRING, FILTER_DYN_STRING, FILTER_PTR_STRING, + FILTER_TRACE_FN, }; #define EVENT_STORAGE_SIZE 128 diff --git a/include/linux/genhd.h b/include/linux/genhd.h index fe23ee768589..e61d3192448e 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -596,6 +596,7 @@ extern char *disk_name (struct gendisk *hd, int partno, char *buf); extern int disk_expand_part_tbl(struct gendisk *disk, int target); extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev); +extern int invalidate_partitions(struct gendisk *disk, struct block_device *bdev); extern struct hd_struct * __must_check add_partition(struct gendisk *disk, int partno, sector_t start, sector_t len, int flags, diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 62b908e0e591..5852545e6bba 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -25,6 +25,173 @@ #ifndef _HYPERV_H #define _HYPERV_H +#include <linux/types.h> + +/* + * An implementation of HyperV key value pair (KVP) functionality for Linux. + * + * + * Copyright (C) 2010, Novell, Inc. + * Author : K. Y. Srinivasan <ksrinivasan@novell.com> + * + */ + +/* + * Maximum value size - used for both key names and value data, and includes + * any applicable NULL terminators. + * + * Note: This limit is somewhat arbitrary, but falls easily within what is + * supported for all native guests (back to Win 2000) and what is reasonable + * for the IC KVP exchange functionality. Note that Windows Me/98/95 are + * limited to 255 character key names. + * + * MSDN recommends not storing data values larger than 2048 bytes in the + * registry. + * + * Note: This value is used in defining the KVP exchange message - this value + * cannot be modified without affecting the message size and compatibility. + */ + +/* + * bytes, including any null terminators + */ +#define HV_KVP_EXCHANGE_MAX_VALUE_SIZE (2048) + + +/* + * Maximum key size - the registry limit for the length of an entry name + * is 256 characters, including the null terminator + */ + +#define HV_KVP_EXCHANGE_MAX_KEY_SIZE (512) + +/* + * In Linux, we implement the KVP functionality in two components: + * 1) The kernel component which is packaged as part of the hv_utils driver + * is responsible for communicating with the host and responsible for + * implementing the host/guest protocol. 2) A user level daemon that is + * responsible for data gathering. + * + * Host/Guest Protocol: The host iterates over an index and expects the guest + * to assign a key name to the index and also return the value corresponding to + * the key. The host will have atmost one KVP transaction outstanding at any + * given point in time. The host side iteration stops when the guest returns + * an error. Microsoft has specified the following mapping of key names to + * host specified index: + * + * Index Key Name + * 0 FullyQualifiedDomainName + * 1 IntegrationServicesVersion + * 2 NetworkAddressIPv4 + * 3 NetworkAddressIPv6 + * 4 OSBuildNumber + * 5 OSName + * 6 OSMajorVersion + * 7 OSMinorVersion + * 8 OSVersion + * 9 ProcessorArchitecture + * + * The Windows host expects the Key Name and Key Value to be encoded in utf16. + * + * Guest Kernel/KVP Daemon Protocol: As noted earlier, we implement all of the + * data gathering functionality in a user mode daemon. The user level daemon + * is also responsible for binding the key name to the index as well. The + * kernel and user-level daemon communicate using a connector channel. + * + * The user mode component first registers with the + * the kernel component. Subsequently, the kernel component requests, data + * for the specified keys. In response to this message the user mode component + * fills in the value corresponding to the specified key. We overload the + * sequence field in the cn_msg header to define our KVP message types. + * + * + * The kernel component simply acts as a conduit for communication between the + * Windows host and the user-level daemon. The kernel component passes up the + * index received from the Host to the user-level daemon. If the index is + * valid (supported), the corresponding key as well as its + * value (both are strings) is returned. If the index is invalid + * (not supported), a NULL key string is returned. + */ + + +/* + * Registry value types. + */ + +#define REG_SZ 1 +#define REG_U32 4 +#define REG_U64 8 + +enum hv_kvp_exchg_op { + KVP_OP_GET = 0, + KVP_OP_SET, + KVP_OP_DELETE, + KVP_OP_ENUMERATE, + KVP_OP_REGISTER, + KVP_OP_COUNT /* Number of operations, must be last. */ +}; + +enum hv_kvp_exchg_pool { + KVP_POOL_EXTERNAL = 0, + KVP_POOL_GUEST, + KVP_POOL_AUTO, + KVP_POOL_AUTO_EXTERNAL, + KVP_POOL_AUTO_INTERNAL, + KVP_POOL_COUNT /* Number of pools, must be last. */ +}; + +struct hv_kvp_hdr { + __u8 operation; + __u8 pool; + __u16 pad; +} __attribute__((packed)); + +struct hv_kvp_exchg_msg_value { + __u32 value_type; + __u32 key_size; + __u32 value_size; + __u8 key[HV_KVP_EXCHANGE_MAX_KEY_SIZE]; + union { + __u8 value[HV_KVP_EXCHANGE_MAX_VALUE_SIZE]; + __u32 value_u32; + __u64 value_u64; + }; +} __attribute__((packed)); + +struct hv_kvp_msg_enumerate { + __u32 index; + struct hv_kvp_exchg_msg_value data; +} __attribute__((packed)); + +struct hv_kvp_msg_get { + struct hv_kvp_exchg_msg_value data; +}; + +struct hv_kvp_msg_set { + struct hv_kvp_exchg_msg_value data; +}; + +struct hv_kvp_msg_delete { + __u32 key_size; + __u8 key[HV_KVP_EXCHANGE_MAX_KEY_SIZE]; +}; + +struct hv_kvp_register { + __u8 version[HV_KVP_EXCHANGE_MAX_KEY_SIZE]; +}; + +struct hv_kvp_msg { + struct hv_kvp_hdr kvp_hdr; + union { + struct hv_kvp_msg_get kvp_get; + struct hv_kvp_msg_set kvp_set; + struct hv_kvp_msg_delete kvp_delete; + struct hv_kvp_msg_enumerate kvp_enum_data; + struct hv_kvp_register kvp_register; + } body; +} __attribute__((packed)); + +#ifdef __KERNEL__ #include <linux/scatterlist.h> #include <linux/list.h> #include <linux/uuid.h> @@ -35,7 +202,7 @@ #include <linux/mod_devicetable.h> -#define MAX_PAGE_BUFFER_COUNT 18 +#define MAX_PAGE_BUFFER_COUNT 19 #define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */ #pragma pack(push, 1) @@ -785,6 +952,7 @@ void vmbus_driver_unregister(struct hv_driver *hv_driver); #define HV_S_OK 0x00000000 #define HV_E_FAIL 0x80004005 +#define HV_S_CONT 0x80070103 #define HV_ERROR_NOT_SUPPORTED 0x80070032 #define HV_ERROR_MACHINE_LOCKED 0x800704F7 @@ -870,4 +1038,9 @@ struct hyperv_service_callback { extern void vmbus_prep_negotiate_resp(struct icmsg_hdr *, struct icmsg_negotiate *, u8 *); +int hv_kvp_init(struct hv_util_service *); +void hv_kvp_deinit(void); +void hv_kvp_onchannelcallback(void *); + +#endif /* __KERNEL__ */ #endif /* _HYPERV_H */ diff --git a/include/linux/if_link.h b/include/linux/if_link.h index c52d4b5f872a..4b24ff453aee 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -137,6 +137,7 @@ enum { IFLA_AF_SPEC, IFLA_GROUP, /* Group the device belongs to */ IFLA_NET_NS_FD, + IFLA_EXT_MASK, /* Extended info mask, VFs, etc */ __IFLA_MAX }; diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 9c66b1ada9d7..f994d51f70f2 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -149,7 +149,7 @@ extern struct cred init_cred; }, \ .rt = { \ .run_list = LIST_HEAD_INIT(tsk.rt.run_list), \ - .time_slice = HZ, \ + .time_slice = RR_TIMESLICE, \ .nr_cpus_allowed = NR_CPUS, \ }, \ .tasks = LIST_HEAD_INIT(tsk.tasks), \ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a64b00e286f5..3f830e005118 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -20,7 +20,6 @@ #include <linux/atomic.h> #include <asm/ptrace.h> #include <asm/system.h> -#include <trace/events/irq.h> /* * These correspond to the IORESOURCE_IRQ_* defines in @@ -456,11 +455,7 @@ asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); -static inline void __raise_softirq_irqoff(unsigned int nr) -{ - trace_softirq_raise(nr); - or_softirq_pending(1UL << nr); -} +extern void __raise_softirq_irqoff(unsigned int nr); extern void raise_softirq_irqoff(unsigned int nr); extern void raise_softirq(unsigned int nr); diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 7e1371c4bccf..1a3018063034 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -6,8 +6,11 @@ #include <linux/workqueue.h> enum { - ICQ_IOPRIO_CHANGED, - ICQ_CGROUP_CHANGED, + ICQ_IOPRIO_CHANGED = 1 << 0, + ICQ_CGROUP_CHANGED = 1 << 1, + ICQ_EXITED = 1 << 2, + + ICQ_CHANGED_MASK = ICQ_IOPRIO_CHANGED | ICQ_CGROUP_CHANGED, }; /* @@ -88,7 +91,7 @@ struct io_cq { struct rcu_head __rcu_head; }; - unsigned long changed; + unsigned int flags; }; /* @@ -133,16 +136,16 @@ static inline struct io_context *ioc_task_link(struct io_context *ioc) struct task_struct; #ifdef CONFIG_BLOCK -void put_io_context(struct io_context *ioc, struct request_queue *locked_q); +void put_io_context(struct io_context *ioc); void exit_io_context(struct task_struct *task); struct io_context *get_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node); void ioc_ioprio_changed(struct io_context *ioc, int ioprio); void ioc_cgroup_changed(struct io_context *ioc); +unsigned int icq_get_changed(struct io_cq *icq); #else struct io_context; -static inline void put_io_context(struct io_context *ioc, - struct request_queue *locked_q) { } +static inline void put_io_context(struct io_context *ioc) { } static inline void exit_io_context(struct task_struct *task) { } #endif diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 5ce8b140428f..c513a40510f5 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -1,22 +1,69 @@ #ifndef _LINUX_JUMP_LABEL_H #define _LINUX_JUMP_LABEL_H +/* + * Jump label support + * + * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com> + * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com> + * + * Jump labels provide an interface to generate dynamic branches using + * self-modifying code. Assuming toolchain and architecture support the result + * of a "if (static_key_false(&key))" statement is a unconditional branch (which + * defaults to false - and the true block is placed out of line). + * + * However at runtime we can change the branch target using + * static_key_slow_{inc,dec}(). These function as a 'reference' count on the key + * object and for as long as there are references all branches referring to + * that particular key will point to the (out of line) true block. + * + * Since this relies on modifying code the static_key_slow_{inc,dec}() functions + * must be considered absolute slow paths (machine wide synchronization etc.). + * OTOH, since the affected branches are unconditional their runtime overhead + * will be absolutely minimal, esp. in the default (off) case where the total + * effect is a single NOP of appropriate size. The on case will patch in a jump + * to the out-of-line block. + * + * When the control is directly exposed to userspace it is prudent to delay the + * decrement to avoid high frequency code modifications which can (and do) + * cause significant performance degradation. Struct static_key_deferred and + * static_key_slow_dec_deferred() provide for this. + * + * Lacking toolchain and or architecture support, it falls back to a simple + * conditional branch. + * + * struct static_key my_key = STATIC_KEY_INIT_TRUE; + * + * if (static_key_true(&my_key)) { + * } + * + * will result in the true case being in-line and starts the key with a single + * reference. Mixing static_key_true() and static_key_false() on the same key is not + * allowed. + * + * Not initializing the key (static data is initialized to 0s anyway) is the + * same as using STATIC_KEY_INIT_FALSE and static_key_false() is + * equivalent with static_branch(). + * +*/ + #include <linux/types.h> #include <linux/compiler.h> #include <linux/workqueue.h> #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) -struct jump_label_key { +struct static_key { atomic_t enabled; +/* Set lsb bit to 1 if branch is default true, 0 ot */ struct jump_entry *entries; #ifdef CONFIG_MODULES - struct jump_label_mod *next; + struct static_key_mod *next; #endif }; -struct jump_label_key_deferred { - struct jump_label_key key; +struct static_key_deferred { + struct static_key key; unsigned long timeout; struct delayed_work work; }; @@ -34,13 +81,34 @@ struct module; #ifdef HAVE_JUMP_LABEL -#ifdef CONFIG_MODULES -#define JUMP_LABEL_INIT {ATOMIC_INIT(0), NULL, NULL} -#else -#define JUMP_LABEL_INIT {ATOMIC_INIT(0), NULL} -#endif +#define JUMP_LABEL_TRUE_BRANCH 1UL + +static +inline struct jump_entry *jump_label_get_entries(struct static_key *key) +{ + return (struct jump_entry *)((unsigned long)key->entries + & ~JUMP_LABEL_TRUE_BRANCH); +} -static __always_inline bool static_branch(struct jump_label_key *key) +static inline bool jump_label_get_branch_default(struct static_key *key) +{ + if ((unsigned long)key->entries & JUMP_LABEL_TRUE_BRANCH) + return true; + return false; +} + +static __always_inline bool static_key_false(struct static_key *key) +{ + return arch_static_branch(key); +} + +static __always_inline bool static_key_true(struct static_key *key) +{ + return !static_key_false(key); +} + +/* Deprecated. Please use 'static_key_false() instead. */ +static __always_inline bool static_branch(struct static_key *key) { return arch_static_branch(key); } @@ -56,21 +124,23 @@ extern void arch_jump_label_transform(struct jump_entry *entry, extern void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type); extern int jump_label_text_reserved(void *start, void *end); -extern void jump_label_inc(struct jump_label_key *key); -extern void jump_label_dec(struct jump_label_key *key); -extern void jump_label_dec_deferred(struct jump_label_key_deferred *key); -extern bool jump_label_enabled(struct jump_label_key *key); +extern void static_key_slow_inc(struct static_key *key); +extern void static_key_slow_dec(struct static_key *key); +extern void static_key_slow_dec_deferred(struct static_key_deferred *key); extern void jump_label_apply_nops(struct module *mod); -extern void jump_label_rate_limit(struct jump_label_key_deferred *key, - unsigned long rl); +extern void +jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl); + +#define STATIC_KEY_INIT_TRUE ((struct static_key) \ + { .enabled = ATOMIC_INIT(1), .entries = (void *)1 }) +#define STATIC_KEY_INIT_FALSE ((struct static_key) \ + { .enabled = ATOMIC_INIT(0), .entries = (void *)0 }) #else /* !HAVE_JUMP_LABEL */ #include <linux/atomic.h> -#define JUMP_LABEL_INIT {ATOMIC_INIT(0)} - -struct jump_label_key { +struct static_key { atomic_t enabled; }; @@ -78,30 +148,45 @@ static __always_inline void jump_label_init(void) { } -struct jump_label_key_deferred { - struct jump_label_key key; +struct static_key_deferred { + struct static_key key; }; -static __always_inline bool static_branch(struct jump_label_key *key) +static __always_inline bool static_key_false(struct static_key *key) +{ + if (unlikely(atomic_read(&key->enabled)) > 0) + return true; + return false; +} + +static __always_inline bool static_key_true(struct static_key *key) { - if (unlikely(atomic_read(&key->enabled))) + if (likely(atomic_read(&key->enabled)) > 0) return true; return false; } -static inline void jump_label_inc(struct jump_label_key *key) +/* Deprecated. Please use 'static_key_false() instead. */ +static __always_inline bool static_branch(struct static_key *key) +{ + if (unlikely(atomic_read(&key->enabled)) > 0) + return true; + return false; +} + +static inline void static_key_slow_inc(struct static_key *key) { atomic_inc(&key->enabled); } -static inline void jump_label_dec(struct jump_label_key *key) +static inline void static_key_slow_dec(struct static_key *key) { atomic_dec(&key->enabled); } -static inline void jump_label_dec_deferred(struct jump_label_key_deferred *key) +static inline void static_key_slow_dec_deferred(struct static_key_deferred *key) { - jump_label_dec(&key->key); + static_key_slow_dec(&key->key); } static inline int jump_label_text_reserved(void *start, void *end) @@ -112,23 +197,30 @@ static inline int jump_label_text_reserved(void *start, void *end) static inline void jump_label_lock(void) {} static inline void jump_label_unlock(void) {} -static inline bool jump_label_enabled(struct jump_label_key *key) -{ - return !!atomic_read(&key->enabled); -} - static inline int jump_label_apply_nops(struct module *mod) { return 0; } -static inline void jump_label_rate_limit(struct jump_label_key_deferred *key, +static inline void +jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { } + +#define STATIC_KEY_INIT_TRUE ((struct static_key) \ + { .enabled = ATOMIC_INIT(1) }) +#define STATIC_KEY_INIT_FALSE ((struct static_key) \ + { .enabled = ATOMIC_INIT(0) }) + #endif /* HAVE_JUMP_LABEL */ -#define jump_label_key_enabled ((struct jump_label_key){ .enabled = ATOMIC_INIT(1), }) -#define jump_label_key_disabled ((struct jump_label_key){ .enabled = ATOMIC_INIT(0), }) +#define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE +#define jump_label_enabled static_key_enabled + +static inline bool static_key_enabled(struct static_key *key) +{ + return (atomic_read(&key->enabled) > 0); +} #endif /* _LINUX_JUMP_LABEL_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e8343422240a..d801acb5e680 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -85,6 +85,19 @@ } \ ) +/* + * Multiplies an integer by a fraction, while avoiding unnecessary + * overflow or loss of precision. + */ +#define mult_frac(x, numer, denom)( \ +{ \ + typeof(x) quot = (x) / (denom); \ + typeof(x) rem = (x) % (denom); \ + (quot * (numer)) + ((rem * (numer)) / (denom)); \ +} \ +) + + #define _RET_IP_ (unsigned long)__builtin_return_address(0) #define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index fee66317e071..35f7237ec972 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -15,13 +15,18 @@ #include <linux/errno.h> #include <linux/list.h> +/* + * Keep this list arranged in rough order of priority. Anything listed after + * KMSG_DUMP_OOPS will not be logged by default unless printk.always_kmsg_dump + * is passed to the kernel. + */ enum kmsg_dump_reason { - KMSG_DUMP_OOPS, KMSG_DUMP_PANIC, + KMSG_DUMP_OOPS, + KMSG_DUMP_EMERG, KMSG_DUMP_RESTART, KMSG_DUMP_HALT, KMSG_DUMP_POWEROFF, - KMSG_DUMP_EMERG, }; /** diff --git a/include/linux/math64.h b/include/linux/math64.h index 23fcdfcba81b..b8ba85544721 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -6,6 +6,8 @@ #if BITS_PER_LONG == 64 +#define div64_long(x,y) div64_s64((x),(y)) + /** * div_u64_rem - unsigned 64bit divide with 32bit divisor with remainder * @@ -45,6 +47,8 @@ static inline s64 div64_s64(s64 dividend, s64 divisor) #elif BITS_PER_LONG == 32 +#define div64_long(x,y) div_s64((x),(y)) + #ifndef div_u64_rem static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) { diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 4d34356fe644..b80de520670b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -129,7 +129,6 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, extern void mem_cgroup_replace_page_cache(struct page *oldpage, struct page *newpage); -extern void mem_cgroup_reset_owner(struct page *page); #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP extern int do_swap_account; #endif @@ -392,10 +391,6 @@ static inline void mem_cgroup_replace_page_cache(struct page *oldpage, struct page *newpage) { } - -static inline void mem_cgroup_reset_owner(struct page *page) -{ -} #endif /* CONFIG_CGROUP_MEM_CONT */ #if !defined(CONFIG_CGROUP_MEM_RES_CTLR) || !defined(CONFIG_DEBUG_VM) diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 9f22ba572de0..19a41d1737af 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -217,6 +217,7 @@ struct mmc_card { #define MMC_CARD_SDXC (1<<6) /* card is SDXC */ #define MMC_CARD_REMOVED (1<<7) /* card has been removed */ #define MMC_STATE_HIGHSPEED_200 (1<<8) /* card is in HS200 mode */ +#define MMC_STATE_SLEEP (1<<9) /* card is in sleep state */ unsigned int quirks; /* card quirks */ #define MMC_QUIRK_LENIENT_FN0 (1<<0) /* allow SDIO FN0 writes outside of the VS CCCR range */ #define MMC_QUIRK_BLKSZ_FOR_BYTE_MODE (1<<1) /* use func->cur_blksize */ @@ -382,6 +383,7 @@ static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data) #define mmc_sd_card_uhs(c) ((c)->state & MMC_STATE_ULTRAHIGHSPEED) #define mmc_card_ext_capacity(c) ((c)->state & MMC_CARD_SDXC) #define mmc_card_removed(c) ((c) && ((c)->state & MMC_CARD_REMOVED)) +#define mmc_card_is_sleep(c) ((c)->state & MMC_STATE_SLEEP) #define mmc_card_set_present(c) ((c)->state |= MMC_STATE_PRESENT) #define mmc_card_set_readonly(c) ((c)->state |= MMC_STATE_READONLY) @@ -393,7 +395,9 @@ static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data) #define mmc_sd_card_set_uhs(c) ((c)->state |= MMC_STATE_ULTRAHIGHSPEED) #define mmc_card_set_ext_capacity(c) ((c)->state |= MMC_CARD_SDXC) #define mmc_card_set_removed(c) ((c)->state |= MMC_CARD_REMOVED) +#define mmc_card_set_sleep(c) ((c)->state |= MMC_STATE_SLEEP) +#define mmc_card_clr_sleep(c) ((c)->state &= ~MMC_STATE_SLEEP) /* * Quirk add/remove for MMC products. */ diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index e8779c6d1759..aae5d1f1bb39 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -14,6 +14,8 @@ #ifndef LINUX_MMC_DW_MMC_H #define LINUX_MMC_DW_MMC_H +#include <linux/scatterlist.h> + #define MAX_MCI_SLOTS 2 enum dw_mci_state { @@ -40,7 +42,7 @@ struct mmc_data; * @lock: Spinlock protecting the queue and associated data. * @regs: Pointer to MMIO registers. * @sg: Scatterlist entry currently being processed by PIO code, if any. - * @pio_offset: Offset into the current scatterlist entry. + * @sg_miter: PIO mapping scatterlist iterator. * @cur_slot: The slot which is currently using the controller. * @mrq: The request currently being processed on @cur_slot, * or NULL if the controller is idle. @@ -115,7 +117,7 @@ struct dw_mci { void __iomem *regs; struct scatterlist *sg; - unsigned int pio_offset; + struct sg_mapping_iter sg_miter; struct dw_mci_slot *cur_slot; struct mmc_request *mrq; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 0beba1e5e1ed..ee2b0363c040 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -257,6 +257,7 @@ struct mmc_host { #define MMC_CAP2_HS200_1_2V_SDR (1 << 6) /* can support */ #define MMC_CAP2_HS200 (MMC_CAP2_HS200_1_8V_SDR | \ MMC_CAP2_HS200_1_2V_SDR) +#define MMC_CAP2_BROKEN_VOLTAGE (1 << 7) /* Use the broken voltage */ mmc_pm_flag_t pm_caps; /* supported pm features */ unsigned int power_notify_type; @@ -444,4 +445,23 @@ static inline int mmc_boot_partition_access(struct mmc_host *host) return !(host->caps2 & MMC_CAP2_BOOTPART_NOACC); } +#ifdef CONFIG_MMC_CLKGATE +void mmc_host_clk_hold(struct mmc_host *host); +void mmc_host_clk_release(struct mmc_host *host); +unsigned int mmc_host_clk_rate(struct mmc_host *host); + +#else +static inline void mmc_host_clk_hold(struct mmc_host *host) +{ +} + +static inline void mmc_host_clk_release(struct mmc_host *host) +{ +} + +static inline unsigned int mmc_host_clk_rate(struct mmc_host *host) +{ + return host->ios.clock; +} +#endif #endif /* LINUX_MMC_HOST_H */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 83ac0713ed0a..fb69ad191ad7 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -560,4 +560,25 @@ struct amba_id { #endif }; +/* + * Match x86 CPUs for CPU specific drivers. + * See documentation of "x86_match_cpu" for details. + */ + +struct x86_cpu_id { + __u16 vendor; + __u16 family; + __u16 model; + __u16 feature; /* bit index */ + kernel_ulong_t driver_data; +}; + +#define X86_FEATURE_MATCH(x) \ + { X86_VENDOR_ANY, X86_FAMILY_ANY, X86_MODEL_ANY, x } + +#define X86_VENDOR_ANY 0xffff +#define X86_FAMILY_ANY 0 +#define X86_MODEL_ANY 0 +#define X86_FEATURE_ANY 0 /* Same as FPU, you can't test for that */ + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0eac07c95255..3e5cb2546e4f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -214,8 +214,8 @@ enum { #include <linux/skbuff.h> #ifdef CONFIG_RPS -#include <linux/jump_label.h> -extern struct jump_label_key rps_needed; +#include <linux/static_key.h> +extern struct static_key rps_needed; #endif struct neighbour; @@ -2687,14 +2687,14 @@ int netdev_info(const struct net_device *dev, const char *format, ...); #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) -#if defined(DEBUG) -#define netdev_dbg(__dev, format, args...) \ - netdev_printk(KERN_DEBUG, __dev, format, ##args) -#elif defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) #define netdev_dbg(__dev, format, args...) \ do { \ dynamic_netdev_dbg(__dev, format, ##args); \ } while (0) +#elif defined(DEBUG) +#define netdev_dbg(__dev, format, args...) \ + netdev_printk(KERN_DEBUG, __dev, format, ##args) #else #define netdev_dbg(__dev, format, args...) \ ({ \ diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index b809265607d0..29734be334c1 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -163,13 +163,13 @@ extern struct ctl_path nf_net_ipv4_netfilter_sysctl_path[]; extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; #if defined(CONFIG_JUMP_LABEL) -#include <linux/jump_label.h> -extern struct jump_label_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; +#include <linux/static_key.h> +extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook) { if (__builtin_constant_p(pf) && __builtin_constant_p(hook)) - return static_branch(&nf_hooks_needed[pf][hook]); + return static_key_false(&nf_hooks_needed[pf][hook]); return !list_empty(&nf_hooks[pf][hook]); } diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 8797ed16feb2..4dd5bd6994a8 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -285,8 +285,8 @@ struct ebt_table { struct module *me; }; -#define EBT_ALIGN(s) (((s) + (__alignof__(struct ebt_replace)-1)) & \ - ~(__alignof__(struct ebt_replace)-1)) +#define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \ + ~(__alignof__(struct _xt_align)-1)) extern struct ebt_table *ebt_register_table(struct net *net, const struct ebt_table *table); extern void ebt_unregister_table(struct net *net, struct ebt_table *table); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index a764cef06b73..d6ba9a12591e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -614,7 +614,6 @@ struct nfs_getaclargs { size_t acl_len; unsigned int acl_pgbase; struct page ** acl_pages; - struct page * acl_scratch; struct nfs4_sequence_args seq_args; }; @@ -624,6 +623,7 @@ struct nfs_getaclres { size_t acl_len; size_t acl_data_offset; int acl_flags; + struct page * acl_scratch; struct nfs4_sequence_res seq_res; }; diff --git a/include/linux/of.h b/include/linux/of.h index a75a831e2057..92cf6ad35e0e 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -281,6 +281,14 @@ static inline struct property *of_find_property(const struct device_node *np, return NULL; } +static inline struct device_node *of_find_compatible_node( + struct device_node *from, + const char *type, + const char *compat) +{ + return NULL; +} + static inline int of_property_read_u32_array(const struct device_node *np, const char *propname, u32 *out_values, size_t sz) diff --git a/include/linux/pci.h b/include/linux/pci.h index a16b1df3deff..d4afd703e948 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -946,6 +946,19 @@ int __must_check __pci_register_driver(struct pci_driver *, struct module *, __pci_register_driver(driver, THIS_MODULE, KBUILD_MODNAME) void pci_unregister_driver(struct pci_driver *dev); + +/** + * module_pci_driver() - Helper macro for registering a PCI driver + * @__pci_driver: pci_driver struct + * + * Helper macro for PCI drivers which do not do anything special in module + * init/exit. This eliminates a lot of boilerplate. Each module may only + * use this macro once, and calling it replaces module_init() and module_exit() + */ +#define module_pci_driver(__pci_driver) \ + module_driver(__pci_driver, pci_register_driver, \ + pci_unregister_driver) + void pci_remove_behind_bridge(struct pci_dev *dev); struct pci_driver *pci_dev_driver(const struct pci_dev *dev); int pci_add_dynid(struct pci_driver *drv, diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 32cd1f67462e..21638ae14e07 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -348,9 +348,9 @@ do { \ #define _this_cpu_generic_to_op(pcp, val, op) \ do { \ unsigned long flags; \ - local_irq_save(flags); \ + raw_local_irq_save(flags); \ *__this_cpu_ptr(&(pcp)) op val; \ - local_irq_restore(flags); \ + raw_local_irq_restore(flags); \ } while (0) #ifndef this_cpu_write @@ -449,10 +449,10 @@ do { \ ({ \ typeof(pcp) ret__; \ unsigned long flags; \ - local_irq_save(flags); \ + raw_local_irq_save(flags); \ __this_cpu_add(pcp, val); \ ret__ = __this_cpu_read(pcp); \ - local_irq_restore(flags); \ + raw_local_irq_restore(flags); \ ret__; \ }) @@ -479,10 +479,10 @@ do { \ #define _this_cpu_generic_xchg(pcp, nval) \ ({ typeof(pcp) ret__; \ unsigned long flags; \ - local_irq_save(flags); \ + raw_local_irq_save(flags); \ ret__ = __this_cpu_read(pcp); \ __this_cpu_write(pcp, nval); \ - local_irq_restore(flags); \ + raw_local_irq_restore(flags); \ ret__; \ }) @@ -507,11 +507,11 @@ do { \ ({ \ typeof(pcp) ret__; \ unsigned long flags; \ - local_irq_save(flags); \ + raw_local_irq_save(flags); \ ret__ = __this_cpu_read(pcp); \ if (ret__ == (oval)) \ __this_cpu_write(pcp, nval); \ - local_irq_restore(flags); \ + raw_local_irq_restore(flags); \ ret__; \ }) @@ -544,10 +544,10 @@ do { \ ({ \ int ret__; \ unsigned long flags; \ - local_irq_save(flags); \ + raw_local_irq_save(flags); \ ret__ = __this_cpu_generic_cmpxchg_double(pcp1, pcp2, \ oval1, oval2, nval1, nval2); \ - local_irq_restore(flags); \ + raw_local_irq_restore(flags); \ ret__; \ }) @@ -718,12 +718,13 @@ do { \ # ifndef __this_cpu_add_return_8 # define __this_cpu_add_return_8(pcp, val) __this_cpu_generic_add_return(pcp, val) # endif -# define __this_cpu_add_return(pcp, val) __pcpu_size_call_return2(this_cpu_add_return_, pcp, val) +# define __this_cpu_add_return(pcp, val) \ + __pcpu_size_call_return2(__this_cpu_add_return_, pcp, val) #endif -#define __this_cpu_sub_return(pcp, val) this_cpu_add_return(pcp, -(val)) -#define __this_cpu_inc_return(pcp) this_cpu_add_return(pcp, 1) -#define __this_cpu_dec_return(pcp) this_cpu_add_return(pcp, -1) +#define __this_cpu_sub_return(pcp, val) __this_cpu_add_return(pcp, -(val)) +#define __this_cpu_inc_return(pcp) __this_cpu_add_return(pcp, 1) +#define __this_cpu_dec_return(pcp) __this_cpu_add_return(pcp, -1) #define __this_cpu_generic_xchg(pcp, nval) \ ({ typeof(pcp) ret__; \ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index abb2776be1ba..bd9f55a5958d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -129,11 +129,40 @@ enum perf_event_sample_format { PERF_SAMPLE_PERIOD = 1U << 8, PERF_SAMPLE_STREAM_ID = 1U << 9, PERF_SAMPLE_RAW = 1U << 10, + PERF_SAMPLE_BRANCH_STACK = 1U << 11, - PERF_SAMPLE_MAX = 1U << 11, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 12, /* non-ABI */ }; /* + * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set + * + * If the user does not pass priv level information via branch_sample_type, + * the kernel uses the event's priv level. Branch and event priv levels do + * not have to match. Branch priv level is checked for permissions. + * + * The branch types can be combined, however BRANCH_ANY covers all types + * of branches and therefore it supersedes all the other types. + */ +enum perf_branch_sample_type { + PERF_SAMPLE_BRANCH_USER = 1U << 0, /* user branches */ + PERF_SAMPLE_BRANCH_KERNEL = 1U << 1, /* kernel branches */ + PERF_SAMPLE_BRANCH_HV = 1U << 2, /* hypervisor branches */ + + PERF_SAMPLE_BRANCH_ANY = 1U << 3, /* any branch types */ + PERF_SAMPLE_BRANCH_ANY_CALL = 1U << 4, /* any call branch */ + PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << 5, /* any return branch */ + PERF_SAMPLE_BRANCH_IND_CALL = 1U << 6, /* indirect calls */ + + PERF_SAMPLE_BRANCH_MAX = 1U << 7, /* non-ABI */ +}; + +#define PERF_SAMPLE_BRANCH_PLM_ALL \ + (PERF_SAMPLE_BRANCH_USER|\ + PERF_SAMPLE_BRANCH_KERNEL|\ + PERF_SAMPLE_BRANCH_HV) + +/* * The format of the data returned by read() on a perf event fd, * as specified by attr.read_format: * @@ -163,6 +192,8 @@ enum perf_event_read_format { }; #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ +#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */ +#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */ /* * Hardware event_id to monitor via a performance monitoring event: @@ -240,6 +271,7 @@ struct perf_event_attr { __u64 bp_len; __u64 config2; /* extension of config1 */ }; + __u64 branch_sample_type; /* enum branch_sample_type */ }; /* @@ -291,12 +323,14 @@ struct perf_event_mmap_page { __s64 offset; /* add to hardware event value */ __u64 time_enabled; /* time event active */ __u64 time_running; /* time event on cpu */ + __u32 time_mult, time_shift; + __u64 time_offset; /* * Hole for extension of the self monitor capabilities */ - __u64 __reserved[123]; /* align to 1k */ + __u64 __reserved[121]; /* align to 1k */ /* * Control data for the mmap() data buffer. @@ -456,6 +490,8 @@ enum perf_event_type { * * { u32 size; * char data[size];}&& PERF_SAMPLE_RAW + * + * { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK * }; */ PERF_RECORD_SAMPLE = 9, @@ -512,7 +548,7 @@ struct perf_guest_info_callbacks { #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/irq_work.h> -#include <linux/jump_label.h> +#include <linux/static_key.h> #include <linux/atomic.h> #include <asm/local.h> @@ -528,12 +564,34 @@ struct perf_raw_record { void *data; }; +/* + * single taken branch record layout: + * + * from: source instruction (may not always be a branch insn) + * to: branch target + * mispred: branch target was mispredicted + * predicted: branch target was predicted + * + * support for mispred, predicted is optional. In case it + * is not supported mispred = predicted = 0. + */ struct perf_branch_entry { - __u64 from; - __u64 to; - __u64 flags; + __u64 from; + __u64 to; + __u64 mispred:1, /* target mispredicted */ + predicted:1,/* target predicted */ + reserved:62; }; +/* + * branch stack layout: + * nr: number of taken branches stored in entries[] + * + * Note that nr can vary from sample to sample + * branches (to, from) are stored from most recent + * to least recent, i.e., entries[0] contains the most + * recent branch. + */ struct perf_branch_stack { __u64 nr; struct perf_branch_entry entries[0]; @@ -564,7 +622,9 @@ struct hw_perf_event { unsigned long event_base; int idx; int last_cpu; + struct hw_perf_event_extra extra_reg; + struct hw_perf_event_extra branch_reg; }; struct { /* software */ struct hrtimer hrtimer; @@ -616,6 +676,7 @@ struct pmu { struct list_head entry; struct device *dev; + const struct attribute_group **attr_groups; char *name; int type; @@ -681,6 +742,17 @@ struct pmu { * for each successful ->add() during the transaction. */ void (*cancel_txn) (struct pmu *pmu); /* optional */ + + /* + * Will return the value for perf_event_mmap_page::index for this event, + * if no implementation is provided it will default to: event->hw.idx + 1. + */ + int (*event_idx) (struct perf_event *event); /*optional */ + + /* + * flush branch stack on context-switches (needed in cpu-wide mode) + */ + void (*flush_branch_stack) (void); }; /** @@ -850,6 +922,9 @@ struct perf_event { #ifdef CONFIG_EVENT_TRACING struct ftrace_event_call *tp_event; struct event_filter *filter; +#ifdef CONFIG_FUNCTION_TRACER + struct ftrace_ops ftrace_ops; +#endif #endif #ifdef CONFIG_CGROUP_PERF @@ -911,7 +986,8 @@ struct perf_event_context { u64 parent_gen; u64 generation; int pin_count; - int nr_cgroups; /* cgroup events present */ + int nr_cgroups; /* cgroup evts */ + int nr_branch_stack; /* branch_stack evt */ struct rcu_head rcu_head; }; @@ -976,6 +1052,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); + struct perf_sample_data { u64 type; @@ -995,12 +1072,14 @@ struct perf_sample_data { u64 period; struct perf_callchain_entry *callchain; struct perf_raw_record *raw; + struct perf_branch_stack *br_stack; }; static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr) { data->addr = addr; data->raw = NULL; + data->br_stack = NULL; } extern void perf_output_sample(struct perf_output_handle *handle, @@ -1029,7 +1108,7 @@ static inline int is_software_event(struct perf_event *event) return event->pmu->task_ctx_nr == perf_sw_context; } -extern struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; +extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); @@ -1057,7 +1136,7 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { struct pt_regs hot_regs; - if (static_branch(&perf_swevent_enabled[event_id])) { + if (static_key_false(&perf_swevent_enabled[event_id])) { if (!regs) { perf_fetch_caller_regs(&hot_regs); regs = &hot_regs; @@ -1066,12 +1145,12 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) } } -extern struct jump_label_key_deferred perf_sched_events; +extern struct static_key_deferred perf_sched_events; static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { - if (static_branch(&perf_sched_events.key)) + if (static_key_false(&perf_sched_events.key)) __perf_event_task_sched_in(prev, task); } @@ -1080,7 +1159,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev, { perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0); - if (static_branch(&perf_sched_events.key)) + if (static_key_false(&perf_sched_events.key)) __perf_event_task_sched_out(prev, next); } @@ -1139,6 +1218,11 @@ extern void perf_bp_event(struct perf_event *event, void *data); # define perf_instruction_pointer(regs) instruction_pointer(regs) #endif +static inline bool has_branch_stack(struct perf_event *event) +{ + return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; +} + extern int perf_output_begin(struct perf_output_handle *handle, struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 58969b2a8a82..5a710b9c578e 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -48,12 +48,14 @@ do { \ barrier(); \ } while (0) -#define preempt_enable_no_resched() \ +#define sched_preempt_enable_no_resched() \ do { \ barrier(); \ dec_preempt_count(); \ } while (0) +#define preempt_enable_no_resched() sched_preempt_enable_no_resched() + #define preempt_enable() \ do { \ preempt_enable_no_resched(); \ @@ -92,6 +94,7 @@ do { \ #else /* !CONFIG_PREEMPT_COUNT */ #define preempt_disable() do { } while (0) +#define sched_preempt_enable_no_resched() do { } while (0) #define preempt_enable_no_resched() do { } while (0) #define preempt_enable() do { } while (0) diff --git a/include/linux/printk.h b/include/linux/printk.h index f0e22f75143f..0525927f203f 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -101,6 +101,11 @@ asmlinkage __printf(1, 2) __cold int printk(const char *fmt, ...); /* + * Special printk facility for scheduler use only, _DO_NOT_USE_ ! + */ +__printf(1, 2) __cold int printk_sched(const char *fmt, ...); + +/* * Please don't use printk_ratelimit(), because it shares ratelimiting state * with all other unrelated printk_ratelimit() callsites. Instead use * printk_ratelimited() or plain old __ratelimit(). @@ -127,6 +132,11 @@ int printk(const char *s, ...) { return 0; } +static inline __printf(1, 2) __cold +int printk_sched(const char *s, ...) +{ + return 0; +} static inline int printk_ratelimit(void) { return 0; @@ -180,13 +190,13 @@ extern void dump_stack(void) __cold; #endif /* If you are writing a driver, please use dev_dbg instead */ -#if defined(DEBUG) -#define pr_debug(fmt, ...) \ - printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) -#elif defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) /* dynamic_pr_debug() uses pr_fmt() internally so we don't need it here */ #define pr_debug(fmt, ...) \ dynamic_pr_debug(fmt, ##__VA_ARGS__) +#elif defined(DEBUG) +#define pr_debug(fmt, ...) \ + printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) diff --git a/include/linux/proportions.h b/include/linux/proportions.h index ef35bb73f69b..26a8a4ed9b07 100644 --- a/include/linux/proportions.h +++ b/include/linux/proportions.h @@ -81,7 +81,11 @@ void prop_inc_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl) * Limit the time part in order to ensure there are some bits left for the * cycle counter and fraction multiply. */ +#if BITS_PER_LONG == 32 #define PROP_MAX_SHIFT (3*BITS_PER_LONG/4) +#else +#define PROP_MAX_SHIFT (BITS_PER_LONG/2) +#endif #define PROP_FRAC_SHIFT (BITS_PER_LONG - PROP_MAX_SHIFT - 1) #define PROP_FRAC_BASE (1UL << PROP_FRAC_SHIFT) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 81c04f4348ec..937217425c47 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -190,6 +190,33 @@ extern void rcu_idle_exit(void); extern void rcu_irq_enter(void); extern void rcu_irq_exit(void); +/** + * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers + * @a: Code that RCU needs to pay attention to. + * + * RCU, RCU-bh, and RCU-sched read-side critical sections are forbidden + * in the inner idle loop, that is, between the rcu_idle_enter() and + * the rcu_idle_exit() -- RCU will happily ignore any such read-side + * critical sections. However, things like powertop need tracepoints + * in the inner idle loop. + * + * This macro provides the way out: RCU_NONIDLE(do_something_with_RCU()) + * will tell RCU that it needs to pay attending, invoke its argument + * (in this example, a call to the do_something_with_RCU() function), + * and then tell RCU to go back to ignoring this CPU. It is permissible + * to nest RCU_NONIDLE() wrappers, but the nesting level is currently + * quite limited. If deeper nesting is required, it will be necessary + * to adjust DYNTICK_TASK_NESTING_VALUE accordingly. + * + * This macro may be used from process-level code only. + */ +#define RCU_NONIDLE(a) \ + do { \ + rcu_idle_exit(); \ + do { a; } while (0); \ + rcu_idle_enter(); \ + } while (0) + /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. @@ -226,6 +253,15 @@ static inline void destroy_rcu_head_on_stack(struct rcu_head *head) } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) +bool rcu_lockdep_current_cpu_online(void); +#else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ +static inline bool rcu_lockdep_current_cpu_online(void) +{ + return 1; +} +#endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC #ifdef CONFIG_PROVE_RCU @@ -239,13 +275,11 @@ static inline int rcu_is_cpu_idle(void) static inline void rcu_lock_acquire(struct lockdep_map *map) { - WARN_ON_ONCE(rcu_is_cpu_idle()); lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { - WARN_ON_ONCE(rcu_is_cpu_idle()); lock_release(map, 1, _THIS_IP_); } @@ -270,6 +304,9 @@ extern int debug_lockdep_rcu_enabled(void); * occur in the same context, for example, it is illegal to invoke * rcu_read_unlock() in process context if the matching rcu_read_lock() * was invoked from within an irq handler. + * + * Note that rcu_read_lock() is disallowed if the CPU is either idle or + * offline from an RCU perspective, so check for those as well. */ static inline int rcu_read_lock_held(void) { @@ -277,6 +314,8 @@ static inline int rcu_read_lock_held(void) return 1; if (rcu_is_cpu_idle()) return 0; + if (!rcu_lockdep_current_cpu_online()) + return 0; return lock_is_held(&rcu_lock_map); } @@ -313,6 +352,9 @@ extern int rcu_read_lock_bh_held(void); * notice an extended quiescent state to other CPUs that started a grace * period. Otherwise we would delay any grace period as long as we run in * the idle task. + * + * Similarly, we avoid claiming an SRCU read lock held if the current + * CPU is offline. */ #ifdef CONFIG_PREEMPT_COUNT static inline int rcu_read_lock_sched_held(void) @@ -323,6 +365,8 @@ static inline int rcu_read_lock_sched_held(void) return 1; if (rcu_is_cpu_idle()) return 0; + if (!rcu_lockdep_current_cpu_online()) + return 0; if (debug_locks) lockdep_opinion = lock_is_held(&rcu_sched_lock_map); return lockdep_opinion || preempt_count() != 0 || irqs_disabled(); @@ -381,8 +425,22 @@ extern int rcu_my_thread_group_empty(void); } \ } while (0) +#if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) +static inline void rcu_preempt_sleep_check(void) +{ + rcu_lockdep_assert(!lock_is_held(&rcu_lock_map), + "Illegal context switch in RCU read-side " + "critical section"); +} +#else /* #ifdef CONFIG_PROVE_RCU */ +static inline void rcu_preempt_sleep_check(void) +{ +} +#endif /* #else #ifdef CONFIG_PROVE_RCU */ + #define rcu_sleep_check() \ do { \ + rcu_preempt_sleep_check(); \ rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh" \ " read-side critical section"); \ @@ -470,6 +528,13 @@ extern int rcu_my_thread_group_empty(void); * NULL. Although rcu_access_pointer() may also be used in cases where * update-side locks prevent the value of the pointer from changing, you * should instead use rcu_dereference_protected() for this use case. + * + * It is also permissible to use rcu_access_pointer() when read-side + * access to the pointer was removed at least one grace period ago, as + * is the case in the context of the RCU callback that is freeing up + * the data, or after a synchronize_rcu() returns. This can be useful + * when tearing down multi-linked structures after a grace period + * has elapsed. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu) @@ -659,6 +724,8 @@ static inline void rcu_read_lock(void) __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_lock() used illegally while idle"); } /* @@ -678,6 +745,8 @@ static inline void rcu_read_lock(void) */ static inline void rcu_read_unlock(void) { + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_unlock() used illegally while idle"); rcu_lock_release(&rcu_lock_map); __release(RCU); __rcu_read_unlock(); @@ -705,6 +774,8 @@ static inline void rcu_read_lock_bh(void) local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_lock_bh() used illegally while idle"); } /* @@ -714,6 +785,8 @@ static inline void rcu_read_lock_bh(void) */ static inline void rcu_read_unlock_bh(void) { + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); @@ -737,6 +810,8 @@ static inline void rcu_read_lock_sched(void) preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ @@ -753,6 +828,8 @@ static inline notrace void rcu_read_lock_sched_notrace(void) */ static inline void rcu_read_unlock_sched(void) { + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); @@ -841,7 +918,7 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset) /* See the kfree_rcu() header comment. */ BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); - call_rcu(head, (rcu_callback)offset); + kfree_call_rcu(head, (rcu_callback)offset); } /** diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 00b7a5e493d2..e93df77176d1 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -27,13 +27,9 @@ #include <linux/cache.h> -#ifdef CONFIG_RCU_BOOST static inline void rcu_init(void) { } -#else /* #ifdef CONFIG_RCU_BOOST */ -void rcu_init(void); -#endif /* #else #ifdef CONFIG_RCU_BOOST */ static inline void rcu_barrier_bh(void) { @@ -83,6 +79,12 @@ static inline void synchronize_sched_expedited(void) synchronize_sched(); } +static inline void kfree_call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *rcu)) +{ + call_rcu(head, func); +} + #ifdef CONFIG_TINY_RCU static inline void rcu_preempt_note_context_switch(void) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 67458468f1a8..e8ee5dd0854c 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -61,6 +61,24 @@ extern void synchronize_rcu_bh(void); extern void synchronize_sched_expedited(void); extern void synchronize_rcu_expedited(void); +void kfree_call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); + +/** + * synchronize_rcu_bh_expedited - Brute-force RCU-bh grace period + * + * Wait for an RCU-bh grace period to elapse, but use a "big hammer" + * approach to force the grace period to end quickly. This consumes + * significant time on all CPUs and is unfriendly to real-time workloads, + * so is thus not recommended for any sort of common-case code. In fact, + * if you are using synchronize_rcu_bh_expedited() in a loop, please + * restructure your code to batch your updates, and then use a single + * synchronize_rcu_bh() instead. + * + * Note that it is illegal to call this function while holding any lock + * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal + * to call this function from a CPU-hotplug notifier. Failing to observe + * these restriction will result in deadlock. + */ static inline void synchronize_rcu_bh_expedited(void) { synchronize_sched_expedited(); @@ -83,6 +101,7 @@ extern void rcu_sched_force_quiescent_state(void); /* A context switch is a grace period for RCU-sched and RCU-bh. */ static inline int rcu_blocking_is_gp(void) { + might_sleep(); /* Check for RCU read-side critical section. */ return num_online_cpus() == 1; } diff --git a/include/linux/regset.h b/include/linux/regset.h index 8abee6556223..686f37327a49 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -335,8 +335,11 @@ static inline int copy_regset_to_user(struct task_struct *target, { const struct user_regset *regset = &view->regsets[setno]; + if (!regset->get) + return -EOPNOTSUPP; + if (!access_ok(VERIFY_WRITE, data, size)) - return -EIO; + return -EFAULT; return regset->get(target, regset, offset, size, NULL, data); } @@ -358,8 +361,11 @@ static inline int copy_regset_from_user(struct task_struct *target, { const struct user_regset *regset = &view->regsets[setno]; + if (!regset->set) + return -EOPNOTSUPP; + if (!access_ok(VERIFY_READ, data, size)) - return -EIO; + return -EFAULT; return regset->set(target, regset, offset, size, NULL, data); } diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 8e872ead88b5..577592ea0ea0 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -602,6 +602,9 @@ struct tcamsg { #define TCA_ACT_TAB 1 /* attr type must be >=1 */ #define TCAA_MAX 1 +/* New extended info filters for IFLA_EXT_MASK */ +#define RTEXT_FILTER_VF (1 << 0) + /* End of information exported to user level */ #ifdef __KERNEL__ diff --git a/include/linux/sched.h b/include/linux/sched.h index 7d379a6bfd88..e074e1e54f85 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -361,6 +361,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); +extern void schedule_preempt_disabled(void); extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner); struct nsproxy; @@ -905,6 +906,7 @@ struct sched_group_power { * single CPU. */ unsigned int power, power_orig; + unsigned long next_update; /* * Number of busy cpus in this group. */ @@ -1052,6 +1054,8 @@ static inline int test_sd_parent(struct sched_domain *sd, int flag) unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu); unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu); +bool cpus_share_cache(int this_cpu, int that_cpu); + #else /* CONFIG_SMP */ struct sched_domain_attr; @@ -1061,6 +1065,12 @@ partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { } + +static inline bool cpus_share_cache(int this_cpu, int that_cpu) +{ + return true; +} + #endif /* !CONFIG_SMP */ @@ -1225,6 +1235,12 @@ struct sched_rt_entity { #endif }; +/* + * default timeslice is 100 msecs (used only for SCHED_RR tasks). + * Timeslices get refilled after they expire. + */ +#define RR_TIMESLICE (100 * HZ / 1000) + struct rcu_node; enum perf_event_task_context { @@ -1319,6 +1335,11 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; +#ifdef CONFIG_GENERIC_HARDIRQS + /* IRQ handler threads */ + unsigned irq_thread:1; +#endif + pid_t pid; pid_t tgid; @@ -1427,11 +1448,6 @@ struct task_struct { * mempolicy */ spinlock_t alloc_lock; -#ifdef CONFIG_GENERIC_HARDIRQS - /* IRQ handler threads */ - struct irqaction *irqaction; -#endif - /* Protection of the PI data structures: */ raw_spinlock_t pi_lock; @@ -1777,7 +1793,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * /* * Per process flags */ -#define PF_STARTING 0x00000002 /* being created */ #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ @@ -1864,8 +1879,7 @@ extern void task_clear_jobctl_pending(struct task_struct *task, #ifdef CONFIG_PREEMPT_RCU #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */ -#define RCU_READ_UNLOCK_BOOSTED (1 << 1) /* boosted while in RCU read-side. */ -#define RCU_READ_UNLOCK_NEED_QS (1 << 2) /* RCU core needs CPU response. */ +#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */ static inline void rcu_copy_process(struct task_struct *p) { @@ -2049,7 +2063,7 @@ extern void sched_autogroup_fork(struct signal_struct *sig); extern void sched_autogroup_exit(struct signal_struct *sig); #ifdef CONFIG_PROC_FS extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m); -extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice); +extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice); #endif #else static inline void sched_autogroup_create_attach(struct task_struct *p) { } @@ -2066,12 +2080,20 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice; extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); extern void rt_mutex_adjust_pi(struct task_struct *p); +static inline bool tsk_is_pi_blocked(struct task_struct *tsk) +{ + return tsk->pi_blocked_on != NULL; +} #else static inline int rt_mutex_getprio(struct task_struct *p) { return p->normal_prio; } # define rt_mutex_adjust_pi(p) do { } while (0) +static inline bool tsk_is_pi_blocked(struct task_struct *tsk) +{ + return false; +} #endif extern bool yield_to(struct task_struct *p, bool preempt); @@ -2371,7 +2393,7 @@ static inline int thread_group_empty(struct task_struct *p) * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also * pins the final release of task.io_context. Also protects ->cpuset and - * ->cgroup.subsys[]. + * ->cgroup.subsys[]. And ->vfork_done. * * Nests both inside and outside of read_lock(&tasklist_lock). * It must not be nested with write_lock_irq(&tasklist_lock), @@ -2390,12 +2412,15 @@ static inline void task_unlock(struct task_struct *p) extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, unsigned long *flags); -#define lock_task_sighand(tsk, flags) \ -({ struct sighand_struct *__ss; \ - __cond_lock(&(tsk)->sighand->siglock, \ - (__ss = __lock_task_sighand(tsk, flags))); \ - __ss; \ -}) \ +static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk, + unsigned long *flags) +{ + struct sighand_struct *ret; + + ret = __lock_task_sighand(tsk, flags); + (void)__cond_lock(&tsk->sighand->siglock, ret); + return ret; +} static inline void unlock_task_sighand(struct task_struct *tsk, unsigned long *flags) diff --git a/include/linux/signalfd.h b/include/linux/signalfd.h index 3ff4961da9b5..247399b2979a 100644 --- a/include/linux/signalfd.h +++ b/include/linux/signalfd.h @@ -61,13 +61,16 @@ static inline void signalfd_notify(struct task_struct *tsk, int sig) wake_up(&tsk->sighand->signalfd_wqh); } +extern void signalfd_cleanup(struct sighand_struct *sighand); + #else /* CONFIG_SIGNALFD */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { } +static inline void signalfd_cleanup(struct sighand_struct *sighand) { } + #endif /* CONFIG_SIGNALFD */ #endif /* __KERNEL__ */ #endif /* _LINUX_SIGNALFD_H */ - diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 50db9b04a552..ae86adee3746 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1465,6 +1465,16 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ +static inline void skb_mac_header_rebuild(struct sk_buff *skb) +{ + if (skb_mac_header_was_set(skb)) { + const unsigned char *old_mac = skb_mac_header(skb); + + skb_set_mac_header(skb, -skb->mac_len); + memmove(skb_mac_header(skb), old_mac, skb->mac_len); + } +} + static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); diff --git a/include/linux/srcu.h b/include/linux/srcu.h index e1b005918bbb..d3d5fa54f25e 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -99,15 +99,18 @@ long srcu_batches_completed(struct srcu_struct *sp); * power mode. This way we can notice an extended quiescent state to * other CPUs that started a grace period. Otherwise we would delay any * grace period as long as we run in the idle task. + * + * Similarly, we avoid claiming an SRCU read lock held if the current + * CPU is offline. */ static inline int srcu_read_lock_held(struct srcu_struct *sp) { - if (rcu_is_cpu_idle()) - return 0; - if (!debug_lockdep_rcu_enabled()) return 1; - + if (rcu_is_cpu_idle()) + return 0; + if (!rcu_lockdep_current_cpu_online()) + return 0; return lock_is_held(&sp->dep_map); } @@ -169,6 +172,8 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) int retval = __srcu_read_lock(sp); rcu_lock_acquire(&(sp)->dep_map); + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "srcu_read_lock() used illegally while idle"); return retval; } @@ -182,6 +187,8 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) static inline void srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp) { + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "srcu_read_unlock() used illegally while idle"); rcu_lock_release(&(sp)->dep_map); __srcu_read_unlock(sp, idx); } diff --git a/include/linux/static_key.h b/include/linux/static_key.h new file mode 100644 index 000000000000..27bd3f8a0857 --- /dev/null +++ b/include/linux/static_key.h @@ -0,0 +1 @@ +#include <linux/jump_label.h> diff --git a/include/linux/sys_soc.h b/include/linux/sys_soc.h new file mode 100644 index 000000000000..2739ccb69571 --- /dev/null +++ b/include/linux/sys_soc.h @@ -0,0 +1,37 @@ +/* + * Copyright (C) ST-Ericsson SA 2011 + * Author: Lee Jones <lee.jones@linaro.org> for ST-Ericsson. + * License terms: GNU General Public License (GPL), version 2 + */ +#ifndef __SOC_BUS_H +#define __SOC_BUS_H + +#include <linux/device.h> + +struct soc_device_attribute { + const char *machine; + const char *family; + const char *revision; + const char *soc_id; +}; + +/** + * soc_device_register - register SoC as a device + * @soc_plat_dev_attr: Attributes passed from platform to be attributed to a SoC + */ +struct soc_device *soc_device_register( + struct soc_device_attribute *soc_plat_dev_attr); + +/** + * soc_device_unregister - unregister SoC device + * @dev: SoC device to be unregistered + */ +void soc_device_unregister(struct soc_device *soc_dev); + +/** + * soc_device_to_device - helper function to fetch struct device + * @soc: Previously registered SoC device container + */ +struct device *soc_device_to_device(struct soc_device *soc); + +#endif /* __SOC_BUS_H */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 515669fa3c1d..8ec1153ff57b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -624,7 +624,7 @@ asmlinkage long sys_socketpair(int, int, int, int __user *); asmlinkage long sys_socketcall(int call, unsigned long __user *args); asmlinkage long sys_listen(int, int); asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, - long timeout); + int timeout); asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); asmlinkage long sys_old_select(struct sel_arg_struct __user *arg); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 46a85c9e1f25..3c7ffdb40dc6 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -412,7 +412,8 @@ struct tcp_sock { struct tcp_sack_block recv_sack_cache[4]; - struct sk_buff *highest_sack; /* highest skb with SACK received + struct sk_buff *highest_sack; /* skb just after the highest + * skb with SACKed bit set * (validity guaranteed only if * sacked_out > 0) */ diff --git a/include/linux/timex.h b/include/linux/timex.h index aa60fe7b6ed6..b75e1864ed19 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -234,23 +234,9 @@ struct timex { extern unsigned long tick_usec; /* USER_HZ period (usec) */ extern unsigned long tick_nsec; /* ACTHZ period (nsec) */ -/* - * phase-lock loop variables - */ -extern int time_status; /* clock synchronization status bits */ - extern void ntp_init(void); extern void ntp_clear(void); -/** - * ntp_synced - Returns 1 if the NTP status is not UNSYNC - * - */ -static inline int ntp_synced(void) -{ - return !(time_status & STA_UNSYNC); -} - /* Required to safely shift negative values */ #define shift_right(x, s) ({ \ __typeof__(x) __x = (x); \ @@ -264,10 +250,9 @@ static inline int ntp_synced(void) #define NTP_INTERVAL_LENGTH (NSEC_PER_SEC/NTP_INTERVAL_FREQ) /* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */ -extern u64 tick_length; +extern u64 ntp_tick_length(void); extern void second_overflow(void); -extern void update_ntp_one_tick(void); extern int do_adjtimex(struct timex *); extern void hardpps(const struct timespec *, const struct timespec *); diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index df0a779c1bbd..bd96ecd0e05c 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -17,7 +17,7 @@ #include <linux/errno.h> #include <linux/types.h> #include <linux/rcupdate.h> -#include <linux/jump_label.h> +#include <linux/static_key.h> struct module; struct tracepoint; @@ -29,7 +29,7 @@ struct tracepoint_func { struct tracepoint { const char *name; /* Tracepoint name */ - struct jump_label_key key; + struct static_key key; void (*regfunc)(void); void (*unregfunc)(void); struct tracepoint_func __rcu *funcs; @@ -114,7 +114,7 @@ static inline void tracepoint_synchronize_unregister(void) * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto". */ -#define __DO_TRACE(tp, proto, args, cond) \ +#define __DO_TRACE(tp, proto, args, cond, prercu, postrcu) \ do { \ struct tracepoint_func *it_func_ptr; \ void *it_func; \ @@ -122,6 +122,7 @@ static inline void tracepoint_synchronize_unregister(void) \ if (!(cond)) \ return; \ + prercu; \ rcu_read_lock_sched_notrace(); \ it_func_ptr = rcu_dereference_sched((tp)->funcs); \ if (it_func_ptr) { \ @@ -132,6 +133,7 @@ static inline void tracepoint_synchronize_unregister(void) } while ((++it_func_ptr)->func); \ } \ rcu_read_unlock_sched_notrace(); \ + postrcu; \ } while (0) /* @@ -139,15 +141,25 @@ static inline void tracepoint_synchronize_unregister(void) * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. */ -#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ +#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ extern struct tracepoint __tracepoint_##name; \ static inline void trace_##name(proto) \ { \ + if (static_key_false(&__tracepoint_##name.key)) \ + __DO_TRACE(&__tracepoint_##name, \ + TP_PROTO(data_proto), \ + TP_ARGS(data_args), \ + TP_CONDITION(cond),,); \ + } \ + static inline void trace_##name##_rcuidle(proto) \ + { \ if (static_branch(&__tracepoint_##name.key)) \ __DO_TRACE(&__tracepoint_##name, \ TP_PROTO(data_proto), \ TP_ARGS(data_args), \ - TP_CONDITION(cond)); \ + TP_CONDITION(cond), \ + rcu_idle_exit(), \ + rcu_idle_enter()); \ } \ static inline int \ register_trace_##name(void (*probe)(data_proto), void *data) \ @@ -176,7 +188,7 @@ static inline void tracepoint_synchronize_unregister(void) __attribute__((section("__tracepoints_strings"))) = #name; \ struct tracepoint __tracepoint_##name \ __attribute__((section("__tracepoints"))) = \ - { __tpstrtab_##name, JUMP_LABEL_INIT, reg, unreg, NULL };\ + { __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL };\ static struct tracepoint * const __tracepoint_ptr_##name __used \ __attribute__((section("__tracepoints_ptrs"))) = \ &__tracepoint_##name; @@ -190,9 +202,11 @@ static inline void tracepoint_synchronize_unregister(void) EXPORT_SYMBOL(__tracepoint_##name) #else /* !CONFIG_TRACEPOINTS */ -#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ +#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ static inline void trace_##name(proto) \ { } \ + static inline void trace_##name##_rcuidle(proto) \ + { } \ static inline int \ register_trace_##name(void (*probe)(data_proto), \ void *data) \ diff --git a/include/linux/usb/ch11.h b/include/linux/usb/ch11.h index 31fdb4c6ee3d..0b83acd3360a 100644 --- a/include/linux/usb/ch11.h +++ b/include/linux/usb/ch11.h @@ -61,12 +61,6 @@ #define USB_PORT_FEAT_TEST 21 #define USB_PORT_FEAT_INDICATOR 22 #define USB_PORT_FEAT_C_PORT_L1 23 -#define USB_PORT_FEAT_C_PORT_LINK_STATE 25 -#define USB_PORT_FEAT_C_PORT_CONFIG_ERROR 26 -#define USB_PORT_FEAT_PORT_REMOTE_WAKE_MASK 27 -#define USB_PORT_FEAT_BH_PORT_RESET 28 -#define USB_PORT_FEAT_C_BH_PORT_RESET 29 -#define USB_PORT_FEAT_FORCE_LINKPM_ACCEPT 30 /* * Port feature selectors added by USB 3.0 spec. @@ -75,8 +69,8 @@ #define USB_PORT_FEAT_LINK_STATE 5 #define USB_PORT_FEAT_U1_TIMEOUT 23 #define USB_PORT_FEAT_U2_TIMEOUT 24 -#define USB_PORT_FEAT_C_LINK_STATE 25 -#define USB_PORT_FEAT_C_CONFIG_ERR 26 +#define USB_PORT_FEAT_C_PORT_LINK_STATE 25 +#define USB_PORT_FEAT_C_PORT_CONFIG_ERROR 26 #define USB_PORT_FEAT_REMOTE_WAKE_MASK 27 #define USB_PORT_FEAT_BH_PORT_RESET 28 #define USB_PORT_FEAT_C_BH_PORT_RESET 29 diff --git a/include/linux/wait.h b/include/linux/wait.h index a9ce45e8501c..7d9a9e990ce6 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -157,7 +157,7 @@ void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode); +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_bit(wait_queue_head_t *, void *, int); int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned); @@ -170,7 +170,8 @@ wait_queue_head_t *bit_waitqueue(void *, int); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) -#define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL) +#define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) +#define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index eb8b9f15f2e0..af155450cabb 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -289,12 +289,16 @@ enum { * * system_freezable_wq is equivalent to system_wq except that it's * freezable. + * + * system_nrt_freezable_wq is equivalent to system_nrt_wq except that + * it's freezable. */ extern struct workqueue_struct *system_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_nrt_wq; extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct *system_freezable_wq; +extern struct workqueue_struct *system_nrt_freezable_wq; extern struct workqueue_struct * __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index abaad6ed9b83..4a82ca0bb0b2 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -256,4 +256,6 @@ void l2cap_exit(void); int sco_init(void); void sco_exit(void); +void bt_sock_reclassify_lock(struct sock *sk, int proto); + #endif /* __BLUETOOTH_H */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index ea9231f4935f..453893b3120e 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -540,7 +540,7 @@ void hci_conn_put_device(struct hci_conn *conn); static inline void hci_conn_hold(struct hci_conn *conn) { atomic_inc(&conn->refcnt); - cancel_delayed_work_sync(&conn->disc_work); + cancel_delayed_work(&conn->disc_work); } static inline void hci_conn_put(struct hci_conn *conn) @@ -559,9 +559,9 @@ static inline void hci_conn_put(struct hci_conn *conn) } else { timeo = msecs_to_jiffies(10); } - cancel_delayed_work_sync(&conn->disc_work); + cancel_delayed_work(&conn->disc_work); queue_delayed_work(conn->hdev->workqueue, - &conn->disc_work, jiffies + timeo); + &conn->disc_work, timeo); } } diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 68f589150692..b1664ed884e6 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -611,7 +611,7 @@ static inline void l2cap_set_timer(struct l2cap_chan *chan, { BT_DBG("chan %p state %d timeout %ld", chan, chan->state, timeout); - if (!__cancel_delayed_work(work)) + if (!cancel_delayed_work(work)) l2cap_chan_hold(chan); schedule_delayed_work(work, timeout); } @@ -619,20 +619,20 @@ static inline void l2cap_set_timer(struct l2cap_chan *chan, static inline void l2cap_clear_timer(struct l2cap_chan *chan, struct delayed_work *work) { - if (__cancel_delayed_work(work)) + if (cancel_delayed_work(work)) l2cap_chan_put(chan); } #define __set_chan_timer(c, t) l2cap_set_timer(c, &c->chan_timer, (t)) #define __clear_chan_timer(c) l2cap_clear_timer(c, &c->chan_timer) #define __set_retrans_timer(c) l2cap_set_timer(c, &c->retrans_timer, \ - L2CAP_DEFAULT_RETRANS_TO); + msecs_to_jiffies(L2CAP_DEFAULT_RETRANS_TO)); #define __clear_retrans_timer(c) l2cap_clear_timer(c, &c->retrans_timer) #define __set_monitor_timer(c) l2cap_set_timer(c, &c->monitor_timer, \ - L2CAP_DEFAULT_MONITOR_TO); + msecs_to_jiffies(L2CAP_DEFAULT_MONITOR_TO)); #define __clear_monitor_timer(c) l2cap_clear_timer(c, &c->monitor_timer) #define __set_ack_timer(c) l2cap_set_timer(c, &chan->ack_timer, \ - L2CAP_DEFAULT_ACK_TO); + msecs_to_jiffies(L2CAP_DEFAULT_ACK_TO)); #define __clear_ack_timer(c) l2cap_clear_timer(c, &c->ack_timer) static inline int __seq_offset(struct l2cap_chan *chan, __u16 seq1, __u16 seq2) @@ -834,7 +834,7 @@ int l2cap_add_scid(struct l2cap_chan *chan, __u16 scid); struct l2cap_chan *l2cap_chan_create(struct sock *sk); void l2cap_chan_close(struct l2cap_chan *chan, int reason); void l2cap_chan_destroy(struct l2cap_chan *chan); -inline int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, +int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, bdaddr_t *dst); int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, u32 priority); diff --git a/include/net/flow.h b/include/net/flow.h index 9b582437fbea..6c469dbdb917 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -93,6 +93,16 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, fl4->fl4_dport = dport; fl4->fl4_sport = sport; } + +/* Reset some input parameters after previous lookup */ +static inline void flowi4_update_output(struct flowi4 *fl4, int oif, __u8 tos, + __be32 daddr, __be32 saddr) +{ + fl4->flowi4_oif = oif; + fl4->flowi4_tos = tos; + fl4->daddr = daddr; + fl4->saddr = saddr; +} struct flowi6 { diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 06b795dd5906..b94765e38e80 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -35,12 +35,12 @@ struct inet_peer { u32 metrics[RTAX_MAX]; u32 rate_tokens; /* rate limiting for ICMP */ - int redirect_genid; unsigned long rate_last; unsigned long pmtu_expires; u32 pmtu_orig; u32 pmtu_learned; struct inetpeer_addr_base redirect_learned; + struct list_head gc_list; /* * Once inet_peer is queued for deletion (refcnt == -1), following fields * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp @@ -96,6 +96,8 @@ static inline struct inet_peer *inet_getpeer_v6(const struct in6_addr *v6daddr, extern void inet_putpeer(struct inet_peer *p); extern bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout); +extern void inetpeer_invalidate_tree(int family); + /* * temporary check to make sure we dont access rid, ip_id_count, tcp_ts, * tcp_ts_stamp if no refcount is taken on inet_peer diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 8a2b0ae7dbd2..ab86036bbf0c 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -209,7 +209,7 @@ extern struct nf_conntrack_tuple_hash * __nf_conntrack_find(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple); -extern void nf_conntrack_hash_insert(struct nf_conn *ct); +extern int nf_conntrack_hash_check_insert(struct nf_conn *ct); extern void nf_ct_delete_from_lists(struct nf_conn *ct); extern void nf_ct_insert_dying_list(struct nf_conn *ct); diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h index 7b2d43139c8e..d58fdec47597 100644 --- a/include/net/netprio_cgroup.h +++ b/include/net/netprio_cgroup.h @@ -37,19 +37,51 @@ extern int net_prio_subsys_id; extern void sock_update_netprioidx(struct sock *sk); -static inline struct cgroup_netprio_state - *task_netprio_state(struct task_struct *p) +#if IS_BUILTIN(CONFIG_NETPRIO_CGROUP) + +static inline u32 task_netprioidx(struct task_struct *p) { -#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) - return container_of(task_subsys_state(p, net_prio_subsys_id), - struct cgroup_netprio_state, css); -#else - return NULL; -#endif + struct cgroup_netprio_state *state; + u32 idx; + + rcu_read_lock(); + state = container_of(task_subsys_state(p, net_prio_subsys_id), + struct cgroup_netprio_state, css); + idx = state->prioidx; + rcu_read_unlock(); + return idx; +} + +#elif IS_MODULE(CONFIG_NETPRIO_CGROUP) + +static inline u32 task_netprioidx(struct task_struct *p) +{ + struct cgroup_netprio_state *state; + int subsys_id; + u32 idx = 0; + + rcu_read_lock(); + subsys_id = rcu_dereference_index_check(net_prio_subsys_id, + rcu_read_lock_held()); + if (subsys_id >= 0) { + state = container_of(task_subsys_state(p, subsys_id), + struct cgroup_netprio_state, css); + idx = state->prioidx; + } + rcu_read_unlock(); + return idx; } #else +static inline u32 task_netprioidx(struct task_struct *p) +{ + return 0; +} + +#endif /* CONFIG_NETPRIO_CGROUP */ + +#else #define sock_update_netprioidx(sk) #endif diff --git a/include/net/route.h b/include/net/route.h index 91855d185b53..b1c0d5b564c2 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -270,6 +270,7 @@ static inline struct rtable *ip_route_connect(struct flowi4 *fl4, if (IS_ERR(rt)) return rt; ip_rt_put(rt); + flowi4_update_output(fl4, oif, tos, fl4->daddr, fl4->saddr); } security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); return ip_route_output_flow(net, fl4, sk); @@ -284,6 +285,9 @@ static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable fl4->fl4_dport = dport; fl4->fl4_sport = sport; ip_rt_put(rt); + flowi4_update_output(fl4, sk->sk_bound_dev_if, + RT_CONN_FLAGS(sk), fl4->daddr, + fl4->saddr); security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); return ip_route_output_flow(sock_net(sk), fl4, sk); } diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 678f1ffaf843..370293901971 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -6,7 +6,7 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, void *); typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); -typedef u16 (*rtnl_calcit_func)(struct sk_buff *); +typedef u16 (*rtnl_calcit_func)(struct sk_buff *, struct nlmsghdr *); extern int __rtnl_register(int protocol, int msgtype, rtnl_doit_func, rtnl_dumpit_func, diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index f6bb08b73ca4..55ce96b53b09 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -220,9 +220,16 @@ struct tcf_proto { struct qdisc_skb_cb { unsigned int pkt_len; - long data[]; + unsigned char data[24]; }; +static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) +{ + struct qdisc_skb_cb *qcb; + BUILD_BUG_ON(sizeof(skb->cb) < sizeof(unsigned int) + sz); + BUILD_BUG_ON(sizeof(qcb->data) < sz); +} + static inline int qdisc_qlen(const struct Qdisc *q) { return q->q.qlen; diff --git a/include/net/sock.h b/include/net/sock.h index 91c1c8baf020..dcde2d9268cd 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -55,7 +55,7 @@ #include <linux/uaccess.h> #include <linux/memcontrol.h> #include <linux/res_counter.h> -#include <linux/jump_label.h> +#include <linux/static_key.h> #include <linux/filter.h> #include <linux/rculist_nulls.h> @@ -924,13 +924,13 @@ inline void sk_refcnt_debug_release(const struct sock *sk) #endif /* SOCK_REFCNT_DEBUG */ #if defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) && defined(CONFIG_NET) -extern struct jump_label_key memcg_socket_limit_enabled; +extern struct static_key memcg_socket_limit_enabled; static inline struct cg_proto *parent_cg_proto(struct proto *proto, struct cg_proto *cg_proto) { return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg)); } -#define mem_cgroup_sockets_enabled static_branch(&memcg_socket_limit_enabled) +#define mem_cgroup_sockets_enabled static_key_false(&memcg_socket_limit_enabled) #else #define mem_cgroup_sockets_enabled 0 static inline struct cg_proto *parent_cg_proto(struct proto *proto, diff --git a/include/net/tcp.h b/include/net/tcp.h index d49db0113a06..2d80c291fffb 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -273,6 +273,14 @@ static inline int between(__u32 seq1, __u32 seq2, __u32 seq3) return seq3 - seq2 >= seq1 - seq2; } +static inline bool tcp_out_of_memory(struct sock *sk) +{ + if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && + sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) + return true; + return false; +} + static inline bool tcp_too_many_orphans(struct sock *sk, int shift) { struct percpu_counter *ocp = sk->sk_prot->orphan_count; @@ -283,13 +291,11 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift) if (orphans << shift > sysctl_tcp_max_orphans) return true; } - - if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && - sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) - return true; return false; } +extern bool tcp_check_oom(struct sock *sk, int shift); + /* syncookies: remember time of last synqueue overflow */ static inline void tcp_synq_overflow(struct sock *sk) { @@ -1358,8 +1364,9 @@ static inline void tcp_push_pending_frames(struct sock *sk) } } -/* Start sequence of the highest skb with SACKed bit, valid only if - * sacked > 0 or when the caller has ensured validity by itself. +/* Start sequence of the skb just after the highest skb with SACKed + * bit, valid only if sacked_out > 0 or when the caller has ensured + * validity by itself. */ static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp) { diff --git a/include/trace/events/power.h b/include/trace/events/power.h index 1bcc2a8c00e2..14b38940062b 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -151,6 +151,8 @@ enum { events get removed */ static inline void trace_power_start(u64 type, u64 state, u64 cpuid) {}; static inline void trace_power_end(u64 cpuid) {}; +static inline void trace_power_start_rcuidle(u64 type, u64 state, u64 cpuid) {}; +static inline void trace_power_end_rcuidle(u64 cpuid) {}; static inline void trace_power_frequency(u64 type, u64 state, u64 cpuid) {}; #endif /* _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED */ diff --git a/include/trace/events/printk.h b/include/trace/events/printk.h new file mode 100644 index 000000000000..94ec79cc011a --- /dev/null +++ b/include/trace/events/printk.h @@ -0,0 +1,41 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM printk + +#if !defined(_TRACE_PRINTK_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PRINTK_H + +#include <linux/tracepoint.h> + +TRACE_EVENT_CONDITION(console, + TP_PROTO(const char *log_buf, unsigned start, unsigned end, + unsigned log_buf_len), + + TP_ARGS(log_buf, start, end, log_buf_len), + + TP_CONDITION(start != end), + + TP_STRUCT__entry( + __dynamic_array(char, msg, end - start + 1) + ), + + TP_fast_assign( + if ((start & (log_buf_len - 1)) > (end & (log_buf_len - 1))) { + memcpy(__get_dynamic_array(msg), + log_buf + (start & (log_buf_len - 1)), + log_buf_len - (start & (log_buf_len - 1))); + memcpy((char *)__get_dynamic_array(msg) + + log_buf_len - (start & (log_buf_len - 1)), + log_buf, end & (log_buf_len - 1)); + } else + memcpy(__get_dynamic_array(msg), + log_buf + (start & (log_buf_len - 1)), + end - start); + ((char *)__get_dynamic_array(msg))[end - start] = 0; + ), + + TP_printk("%s", __get_str(msg)) +); +#endif /* _TRACE_PRINTK_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index d2d88bed891b..337099783f37 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -313,19 +313,22 @@ TRACE_EVENT(rcu_prep_idle, /* * Tracepoint for the registration of a single RCU callback function. * The first argument is the type of RCU, the second argument is - * a pointer to the RCU callback itself, and the third element is the - * new RCU callback queue length for the current CPU. + * a pointer to the RCU callback itself, the third element is the + * number of lazy callbacks queued, and the fourth element is the + * total number of callbacks queued. */ TRACE_EVENT(rcu_callback, - TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen), + TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen_lazy, + long qlen), - TP_ARGS(rcuname, rhp, qlen), + TP_ARGS(rcuname, rhp, qlen_lazy, qlen), TP_STRUCT__entry( __field(char *, rcuname) __field(void *, rhp) __field(void *, func) + __field(long, qlen_lazy) __field(long, qlen) ), @@ -333,11 +336,13 @@ TRACE_EVENT(rcu_callback, __entry->rcuname = rcuname; __entry->rhp = rhp; __entry->func = rhp->func; + __entry->qlen_lazy = qlen_lazy; __entry->qlen = qlen; ), - TP_printk("%s rhp=%p func=%pf %ld", - __entry->rcuname, __entry->rhp, __entry->func, __entry->qlen) + TP_printk("%s rhp=%p func=%pf %ld/%ld", + __entry->rcuname, __entry->rhp, __entry->func, + __entry->qlen_lazy, __entry->qlen) ); /* @@ -345,20 +350,21 @@ TRACE_EVENT(rcu_callback, * kfree() form. The first argument is the RCU type, the second argument * is a pointer to the RCU callback, the third argument is the offset * of the callback within the enclosing RCU-protected data structure, - * and the fourth argument is the new RCU callback queue length for the - * current CPU. + * the fourth argument is the number of lazy callbacks queued, and the + * fifth argument is the total number of callbacks queued. */ TRACE_EVENT(rcu_kfree_callback, TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset, - long qlen), + long qlen_lazy, long qlen), - TP_ARGS(rcuname, rhp, offset, qlen), + TP_ARGS(rcuname, rhp, offset, qlen_lazy, qlen), TP_STRUCT__entry( __field(char *, rcuname) __field(void *, rhp) __field(unsigned long, offset) + __field(long, qlen_lazy) __field(long, qlen) ), @@ -366,41 +372,45 @@ TRACE_EVENT(rcu_kfree_callback, __entry->rcuname = rcuname; __entry->rhp = rhp; __entry->offset = offset; + __entry->qlen_lazy = qlen_lazy; __entry->qlen = qlen; ), - TP_printk("%s rhp=%p func=%ld %ld", + TP_printk("%s rhp=%p func=%ld %ld/%ld", __entry->rcuname, __entry->rhp, __entry->offset, - __entry->qlen) + __entry->qlen_lazy, __entry->qlen) ); /* * Tracepoint for marking the beginning rcu_do_batch, performed to start * RCU callback invocation. The first argument is the RCU flavor, - * the second is the total number of callbacks (including those that - * are not yet ready to be invoked), and the third argument is the - * current RCU-callback batch limit. + * the second is the number of lazy callbacks queued, the third is + * the total number of callbacks queued, and the fourth argument is + * the current RCU-callback batch limit. */ TRACE_EVENT(rcu_batch_start, - TP_PROTO(char *rcuname, long qlen, int blimit), + TP_PROTO(char *rcuname, long qlen_lazy, long qlen, int blimit), - TP_ARGS(rcuname, qlen, blimit), + TP_ARGS(rcuname, qlen_lazy, qlen, blimit), TP_STRUCT__entry( __field(char *, rcuname) + __field(long, qlen_lazy) __field(long, qlen) __field(int, blimit) ), TP_fast_assign( __entry->rcuname = rcuname; + __entry->qlen_lazy = qlen_lazy; __entry->qlen = qlen; __entry->blimit = blimit; ), - TP_printk("%s CBs=%ld bl=%d", - __entry->rcuname, __entry->qlen, __entry->blimit) + TP_printk("%s CBs=%ld/%ld bl=%d", + __entry->rcuname, __entry->qlen_lazy, __entry->qlen, + __entry->blimit) ); /* @@ -531,16 +541,21 @@ TRACE_EVENT(rcu_torture_read, #else /* #ifdef CONFIG_RCU_TRACE */ #define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0) -#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, qsmask) do { } while (0) +#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \ + qsmask) do { } while (0) #define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0) #define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0) -#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks) do { } while (0) +#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \ + grplo, grphi, gp_tasks) do { } \ + while (0) #define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0) #define trace_rcu_dyntick(polarity, oldnesting, newnesting) do { } while (0) #define trace_rcu_prep_idle(reason) do { } while (0) -#define trace_rcu_callback(rcuname, rhp, qlen) do { } while (0) -#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen) do { } while (0) -#define trace_rcu_batch_start(rcuname, qlen, blimit) do { } while (0) +#define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0) +#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \ + do { } while (0) +#define trace_rcu_batch_start(rcuname, qlen_lazy, qlen, blimit) \ + do { } while (0) #define trace_rcu_invoke_callback(rcuname, rhp) do { } while (0) #define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0) #define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \ diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 6ba596b07a72..fbc7b1ad929b 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -6,6 +6,7 @@ #include <linux/sched.h> #include <linux/tracepoint.h> +#include <linux/binfmts.h> /* * Tracepoint for calling kthread_stop, performed to end a kthread: @@ -276,6 +277,32 @@ TRACE_EVENT(sched_process_fork, ); /* + * Tracepoint for exec: + */ +TRACE_EVENT(sched_process_exec, + + TP_PROTO(struct task_struct *p, pid_t old_pid, + struct linux_binprm *bprm), + + TP_ARGS(p, old_pid, bprm), + + TP_STRUCT__entry( + __string( filename, bprm->filename ) + __field( pid_t, pid ) + __field( pid_t, old_pid ) + ), + + TP_fast_assign( + __assign_str(filename, bprm->filename); + __entry->pid = p->pid; + __entry->old_pid = p->pid; + ), + + TP_printk("filename=%s pid=%d old_pid=%d", __get_str(filename), + __entry->pid, __entry->old_pid) +); + +/* * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE * adding sched_stat support to SCHED_FIFO/RR would be welcome. */ @@ -370,56 +397,6 @@ TRACE_EVENT(sched_stat_runtime, (unsigned long long)__entry->vruntime) ); -#ifdef CREATE_TRACE_POINTS -static inline u64 trace_get_sleeptime(struct task_struct *tsk) -{ -#ifdef CONFIG_SCHEDSTATS - u64 block, sleep; - - block = tsk->se.statistics.block_start; - sleep = tsk->se.statistics.sleep_start; - tsk->se.statistics.block_start = 0; - tsk->se.statistics.sleep_start = 0; - - return block ? block : sleep ? sleep : 0; -#else - return 0; -#endif -} -#endif - -/* - * Tracepoint for accounting sleeptime (time the task is sleeping - * or waiting for I/O). - */ -TRACE_EVENT(sched_stat_sleeptime, - - TP_PROTO(struct task_struct *tsk, u64 now), - - TP_ARGS(tsk, now), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( u64, sleeptime ) - ), - - TP_fast_assign( - memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); - __entry->pid = tsk->pid; - __entry->sleeptime = trace_get_sleeptime(tsk); - __entry->sleeptime = __entry->sleeptime ? - now - __entry->sleeptime : 0; - ) - TP_perf_assign( - __perf_count(__entry->sleeptime); - ), - - TP_printk("comm=%s pid=%d sleeptime=%Lu [ns]", - __entry->comm, __entry->pid, - (unsigned long long)__entry->sleeptime) -); - /* * Tracepoint for showing priority inheritance modifying a tasks * priority. diff --git a/include/trace/events/signal.h b/include/trace/events/signal.h index 17df43464df0..39a8a430d90f 100644 --- a/include/trace/events/signal.h +++ b/include/trace/events/signal.h @@ -23,11 +23,23 @@ } \ } while (0) +#ifndef TRACE_HEADER_MULTI_READ +enum { + TRACE_SIGNAL_DELIVERED, + TRACE_SIGNAL_IGNORED, + TRACE_SIGNAL_ALREADY_PENDING, + TRACE_SIGNAL_OVERFLOW_FAIL, + TRACE_SIGNAL_LOSE_INFO, +}; +#endif + /** * signal_generate - called when a signal is generated * @sig: signal number * @info: pointer to struct siginfo * @task: pointer to struct task_struct + * @group: shared or private + * @result: TRACE_SIGNAL_* * * Current process sends a 'sig' signal to 'task' process with * 'info' siginfo. If 'info' is SEND_SIG_NOINFO or SEND_SIG_PRIV, @@ -37,9 +49,10 @@ */ TRACE_EVENT(signal_generate, - TP_PROTO(int sig, struct siginfo *info, struct task_struct *task), + TP_PROTO(int sig, struct siginfo *info, struct task_struct *task, + int group, int result), - TP_ARGS(sig, info, task), + TP_ARGS(sig, info, task, group, result), TP_STRUCT__entry( __field( int, sig ) @@ -47,6 +60,8 @@ TRACE_EVENT(signal_generate, __field( int, code ) __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) + __field( int, group ) + __field( int, result ) ), TP_fast_assign( @@ -54,11 +69,14 @@ TRACE_EVENT(signal_generate, TP_STORE_SIGINFO(__entry, info); memcpy(__entry->comm, task->comm, TASK_COMM_LEN); __entry->pid = task->pid; + __entry->group = group; + __entry->result = result; ), - TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d", + TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d grp=%d res=%d", __entry->sig, __entry->errno, __entry->code, - __entry->comm, __entry->pid) + __entry->comm, __entry->pid, __entry->group, + __entry->result) ); /** @@ -101,65 +119,6 @@ TRACE_EVENT(signal_deliver, __entry->sa_handler, __entry->sa_flags) ); -DECLARE_EVENT_CLASS(signal_queue_overflow, - - TP_PROTO(int sig, int group, struct siginfo *info), - - TP_ARGS(sig, group, info), - - TP_STRUCT__entry( - __field( int, sig ) - __field( int, group ) - __field( int, errno ) - __field( int, code ) - ), - - TP_fast_assign( - __entry->sig = sig; - __entry->group = group; - TP_STORE_SIGINFO(__entry, info); - ), - - TP_printk("sig=%d group=%d errno=%d code=%d", - __entry->sig, __entry->group, __entry->errno, __entry->code) -); - -/** - * signal_overflow_fail - called when signal queue is overflow - * @sig: signal number - * @group: signal to process group or not (bool) - * @info: pointer to struct siginfo - * - * Kernel fails to generate 'sig' signal with 'info' siginfo, because - * siginfo queue is overflow, and the signal is dropped. - * 'group' is not 0 if the signal will be sent to a process group. - * 'sig' is always one of RT signals. - */ -DEFINE_EVENT(signal_queue_overflow, signal_overflow_fail, - - TP_PROTO(int sig, int group, struct siginfo *info), - - TP_ARGS(sig, group, info) -); - -/** - * signal_lose_info - called when siginfo is lost - * @sig: signal number - * @group: signal to process group or not (bool) - * @info: pointer to struct siginfo - * - * Kernel generates 'sig' signal but loses 'info' siginfo, because siginfo - * queue is overflow. - * 'group' is not 0 if the signal will be sent to a process group. - * 'sig' is always one of non-RT signals. - */ -DEFINE_EVENT(signal_queue_overflow, signal_lose_info, - - TP_PROTO(int sig, int group, struct siginfo *info), - - TP_ARGS(sig, group, info) -); - #endif /* _TRACE_SIGNAL_H */ /* This part must be outside protection */ diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 8588a8918023..5973410e8f8c 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -47,7 +47,10 @@ DECLARE_EVENT_CLASS(writeback_work_class, __field(int, reason) ), TP_fast_assign( - strncpy(__entry->name, dev_name(bdi->dev), 32); + struct device *dev = bdi->dev; + if (!dev) + dev = default_backing_dev_info.dev; + strncpy(__entry->name, dev_name(dev), 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; @@ -426,7 +429,7 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_fast_assign( strncpy(__entry->name, - dev_name(inode->i_mapping->backing_dev_info->dev), 32); + dev_name(inode_to_bdi(inode)->dev), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; |