diff options
Diffstat (limited to 'include')
64 files changed, 972 insertions, 767 deletions
diff --git a/include/linux/audit.h b/include/linux/audit.h index 51b1b7054a23..0050ef288ab3 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -36,6 +36,7 @@ struct mqstat; struct audit_watch; struct audit_tree; struct sk_buff; +struct kern_ipc_perm; struct audit_krule { u32 pflags; diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index b3772edca2e6..e06bad467f55 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -21,6 +21,7 @@ #include <linux/sched.h> #include <linux/printk.h> #include <linux/rcupdate.h> +#include <linux/timekeeping.h> struct dma_fence; struct dma_fence_ops; diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index f2044d5a652b..87e3bedf8eb0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -13,13 +13,13 @@ #define _LINUX_HRTIMER_H #include <linux/hrtimer_defs.h> -#include <linux/rbtree.h> +#include <linux/hrtimer_types.h> #include <linux/init.h> #include <linux/list.h> -#include <linux/percpu.h> +#include <linux/percpu-defs.h> +#include <linux/rbtree.h> #include <linux/seqlock.h> #include <linux/timer.h> -#include <linux/timerqueue.h> struct hrtimer_clock_base; struct hrtimer_cpu_base; @@ -60,14 +60,6 @@ enum hrtimer_mode { }; /* - * Return values for the callback function - */ -enum hrtimer_restart { - HRTIMER_NORESTART, /* Timer is not restarted */ - HRTIMER_RESTART, /* Timer must be restarted */ -}; - -/* * Values to track state of the timer * * Possible states: @@ -95,38 +87,6 @@ enum hrtimer_restart { #define HRTIMER_STATE_ENQUEUED 0x01 /** - * struct hrtimer - the basic hrtimer structure - * @node: timerqueue node, which also manages node.expires, - * the absolute expiry time in the hrtimers internal - * representation. The time is related to the clock on - * which the timer is based. Is setup by adding - * slack to the _softexpires value. For non range timers - * identical to _softexpires. - * @_softexpires: the absolute earliest expiry time of the hrtimer. - * The time which was given as expiry time when the timer - * was armed. - * @function: timer expiry callback function - * @base: pointer to the timer base (per cpu and per clock) - * @state: state information (See bit values above) - * @is_rel: Set if the timer was armed relative - * @is_soft: Set if hrtimer will be expired in soft interrupt context. - * @is_hard: Set if hrtimer will be expired in hard interrupt context - * even on RT. - * - * The hrtimer structure must be initialized by hrtimer_init() - */ -struct hrtimer { - struct timerqueue_node node; - ktime_t _softexpires; - enum hrtimer_restart (*function)(struct hrtimer *); - struct hrtimer_clock_base *base; - u8 state; - u8 is_rel; - u8 is_soft; - u8 is_hard; -}; - -/** * struct hrtimer_sleeper - simple sleeper structure * @timer: embedded timer structure * @task: task to wake up diff --git a/include/linux/hrtimer_types.h b/include/linux/hrtimer_types.h new file mode 100644 index 000000000000..ad66a3081735 --- /dev/null +++ b/include/linux/hrtimer_types.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_HRTIMER_TYPES_H +#define _LINUX_HRTIMER_TYPES_H + +#include <linux/types.h> +#include <linux/timerqueue_types.h> + +struct hrtimer_clock_base; + +/* + * Return values for the callback function + */ +enum hrtimer_restart { + HRTIMER_NORESTART, /* Timer is not restarted */ + HRTIMER_RESTART, /* Timer must be restarted */ +}; + +/** + * struct hrtimer - the basic hrtimer structure + * @node: timerqueue node, which also manages node.expires, + * the absolute expiry time in the hrtimers internal + * representation. The time is related to the clock on + * which the timer is based. Is setup by adding + * slack to the _softexpires value. For non range timers + * identical to _softexpires. + * @_softexpires: the absolute earliest expiry time of the hrtimer. + * The time which was given as expiry time when the timer + * was armed. + * @function: timer expiry callback function + * @base: pointer to the timer base (per cpu and per clock) + * @state: state information (See bit values above) + * @is_rel: Set if the timer was armed relative + * @is_soft: Set if hrtimer will be expired in soft interrupt context. + * @is_hard: Set if hrtimer will be expired in hard interrupt context + * even on RT. + * + * The hrtimer structure must be initialized by hrtimer_init() + */ +struct hrtimer { + struct timerqueue_node node; + ktime_t _softexpires; + enum hrtimer_restart (*function)(struct hrtimer *); + struct hrtimer_clock_base *base; + u8 state; + u8 is_rel; + u8 is_soft; + u8 is_hard; +}; + +#endif /* _LINUX_HRTIMER_TYPES_H */ diff --git a/include/linux/ipc.h b/include/linux/ipc.h index e1c9eea6015b..9b1434247aab 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -2,7 +2,7 @@ #ifndef _LINUX_IPC_H #define _LINUX_IPC_H -#include <linux/spinlock.h> +#include <linux/spinlock_types.h> #include <linux/uidgid.h> #include <linux/rhashtable-types.h> #include <uapi/linux/ipc.h> diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 2b665c32f5fe..147feebd508c 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -12,6 +12,7 @@ #ifndef _LINUX_TRACE_IRQFLAGS_H #define _LINUX_TRACE_IRQFLAGS_H +#include <linux/irqflags_types.h> #include <linux/typecheck.h> #include <linux/cleanup.h> #include <asm/irqflags.h> @@ -34,19 +35,6 @@ #ifdef CONFIG_TRACE_IRQFLAGS -/* Per-task IRQ trace events information. */ -struct irqtrace_events { - unsigned int irq_events; - unsigned long hardirq_enable_ip; - unsigned long hardirq_disable_ip; - unsigned int hardirq_enable_event; - unsigned int hardirq_disable_event; - unsigned long softirq_disable_ip; - unsigned long softirq_enable_ip; - unsigned int softirq_disable_event; - unsigned int softirq_enable_event; -}; - DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); diff --git a/include/linux/irqflags_types.h b/include/linux/irqflags_types.h new file mode 100644 index 000000000000..c13f0d915097 --- /dev/null +++ b/include/linux/irqflags_types.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_IRQFLAGS_TYPES_H +#define _LINUX_IRQFLAGS_TYPES_H + +#ifdef CONFIG_TRACE_IRQFLAGS + +/* Per-task IRQ trace events information. */ +struct irqtrace_events { + unsigned int irq_events; + unsigned long hardirq_enable_ip; + unsigned long hardirq_disable_ip; + unsigned int hardirq_enable_event; + unsigned int hardirq_disable_event; + unsigned long softirq_disable_ip; + unsigned long softirq_enable_ip; + unsigned int softirq_disable_event; + unsigned int softirq_enable_event; +}; + +#endif + +#endif /* _LINUX_IRQFLAGS_TYPES_H */ diff --git a/include/linux/kmsan_types.h b/include/linux/kmsan_types.h index 8bfa6c98176d..929287981afe 100644 --- a/include/linux/kmsan_types.h +++ b/include/linux/kmsan_types.h @@ -9,6 +9,8 @@ #ifndef _LINUX_KMSAN_TYPES_H #define _LINUX_KMSAN_TYPES_H +#include <linux/types.h> + /* These constants are defined in the MSan LLVM instrumentation pass. */ #define KMSAN_RETVAL_SIZE 800 #define KMSAN_PARAM_SIZE 800 diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 73f20deb497d..3a4e723eae0f 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -21,12 +21,10 @@ #ifndef _LINUX_KTIME_H #define _LINUX_KTIME_H -#include <linux/time.h> -#include <linux/jiffies.h> #include <asm/bug.h> - -/* Nanosecond scalar representation for kernel time values */ -typedef s64 ktime_t; +#include <linux/jiffies.h> +#include <linux/time.h> +#include <linux/types.h> /** * ktime_set - Set a ktime_t variable from a seconds/nanoseconds value diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index dc2844b071c2..08b0d1d9d78b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -82,63 +82,6 @@ struct lock_chain { u64 chain_key; }; -#define MAX_LOCKDEP_KEYS_BITS 13 -#define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS) -#define INITIAL_CHAIN_KEY -1 - -struct held_lock { - /* - * One-way hash of the dependency chain up to this point. We - * hash the hashes step by step as the dependency chain grows. - * - * We use it for dependency-caching and we skip detection - * passes and dependency-updates if there is a cache-hit, so - * it is absolutely critical for 100% coverage of the validator - * to have a unique key value for every unique dependency path - * that can occur in the system, to make a unique hash value - * as likely as possible - hence the 64-bit width. - * - * The task struct holds the current hash value (initialized - * with zero), here we store the previous hash value: - */ - u64 prev_chain_key; - unsigned long acquire_ip; - struct lockdep_map *instance; - struct lockdep_map *nest_lock; -#ifdef CONFIG_LOCK_STAT - u64 waittime_stamp; - u64 holdtime_stamp; -#endif - /* - * class_idx is zero-indexed; it points to the element in - * lock_classes this held lock instance belongs to. class_idx is in - * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive. - */ - unsigned int class_idx:MAX_LOCKDEP_KEYS_BITS; - /* - * The lock-stack is unified in that the lock chains of interrupt - * contexts nest ontop of process context chains, but we 'separate' - * the hashes by starting with 0 if we cross into an interrupt - * context, and we also keep do not add cross-context lock - * dependencies - the lock usage graph walking covers that area - * anyway, and we'd just unnecessarily increase the number of - * dependencies otherwise. [Note: hardirq and softirq contexts - * are separated from each other too.] - * - * The following field is used to detect when we cross into an - * interrupt context: - */ - unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */ - unsigned int trylock:1; /* 16 bits */ - - unsigned int read:2; /* see lock_acquire() comment */ - unsigned int check:1; /* see lock_acquire() comment */ - unsigned int hardirqs_off:1; - unsigned int sync:1; - unsigned int references:11; /* 32 bits */ - unsigned int pin_count; -}; - /* * Initialization, self-test and debugging-output methods: */ diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index 857d785e89e6..70d30d40ea4a 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -198,6 +198,63 @@ struct lockdep_map { struct pin_cookie { unsigned int val; }; +#define MAX_LOCKDEP_KEYS_BITS 13 +#define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS) +#define INITIAL_CHAIN_KEY -1 + +struct held_lock { + /* + * One-way hash of the dependency chain up to this point. We + * hash the hashes step by step as the dependency chain grows. + * + * We use it for dependency-caching and we skip detection + * passes and dependency-updates if there is a cache-hit, so + * it is absolutely critical for 100% coverage of the validator + * to have a unique key value for every unique dependency path + * that can occur in the system, to make a unique hash value + * as likely as possible - hence the 64-bit width. + * + * The task struct holds the current hash value (initialized + * with zero), here we store the previous hash value: + */ + u64 prev_chain_key; + unsigned long acquire_ip; + struct lockdep_map *instance; + struct lockdep_map *nest_lock; +#ifdef CONFIG_LOCK_STAT + u64 waittime_stamp; + u64 holdtime_stamp; +#endif + /* + * class_idx is zero-indexed; it points to the element in + * lock_classes this held lock instance belongs to. class_idx is in + * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive. + */ + unsigned int class_idx:MAX_LOCKDEP_KEYS_BITS; + /* + * The lock-stack is unified in that the lock chains of interrupt + * contexts nest ontop of process context chains, but we 'separate' + * the hashes by starting with 0 if we cross into an interrupt + * context, and we also keep do not add cross-context lock + * dependencies - the lock usage graph walking covers that area + * anyway, and we'd just unnecessarily increase the number of + * dependencies otherwise. [Note: hardirq and softirq contexts + * are separated from each other too.] + * + * The following field is used to detect when we cross into an + * interrupt context: + */ + unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */ + unsigned int trylock:1; /* 16 bits */ + + unsigned int read:2; /* see lock_acquire() comment */ + unsigned int check:1; /* see lock_acquire() comment */ + unsigned int hardirqs_off:1; + unsigned int sync:1; + unsigned int references:11; /* 32 bits */ + unsigned int pin_count; +}; + #else /* !CONFIG_LOCKDEP */ /* diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index aa44fff8bb9d..a2f6179b672b 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -9,9 +9,6 @@ */ #include <linux/types.h> -#include <linux/threads.h> -#include <linux/atomic.h> -#include <linux/cpumask.h> #include <asm/page.h> @@ -36,6 +33,8 @@ enum { NR_MM_COUNTERS }; +struct page; + struct page_frag { struct page *page; #if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 95d11308f995..7e208d46ba5b 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -20,6 +20,7 @@ #include <linux/osq_lock.h> #include <linux/debug_locks.h> #include <linux/cleanup.h> +#include <linux/mutex_types.h> #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ @@ -33,49 +34,6 @@ #ifndef CONFIG_PREEMPT_RT -/* - * Simple, straightforward mutexes with strict semantics: - * - * - only one task can hold the mutex at a time - * - only the owner can unlock the mutex - * - multiple unlocks are not permitted - * - recursive locking is not permitted - * - a mutex object must be initialized via the API - * - a mutex object must not be initialized via memset or copying - * - task may not exit with mutex held - * - memory areas where held locks reside must not be freed - * - held mutexes must not be reinitialized - * - mutexes may not be used in hardware or software interrupt - * contexts such as tasklets and timers - * - * These semantics are fully enforced when DEBUG_MUTEXES is - * enabled. Furthermore, besides enforcing the above rules, the mutex - * debugging code also implements a number of additional features - * that make lock debugging easier and faster: - * - * - uses symbolic names of mutexes, whenever they are printed in debug output - * - point-of-acquire tracking, symbolic lookup of function names - * - list of all locks held in the system, printout of them - * - owner tracking - * - detects self-recursing locks and prints out all relevant info - * - detects multi-task circular deadlocks and prints out all affected - * locks and tasks (and only those tasks) - */ -struct mutex { - atomic_long_t owner; - raw_spinlock_t wait_lock; -#ifdef CONFIG_MUTEX_SPIN_ON_OWNER - struct optimistic_spin_queue osq; /* Spinner MCS lock */ -#endif - struct list_head wait_list; -#ifdef CONFIG_DEBUG_MUTEXES - void *magic; -#endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; - #ifdef CONFIG_DEBUG_MUTEXES #define __DEBUG_MUTEX_INITIALIZER(lockname) \ @@ -131,14 +89,6 @@ extern bool mutex_is_locked(struct mutex *lock); /* * Preempt-RT variant based on rtmutexes. */ -#include <linux/rtmutex.h> - -struct mutex { - struct rt_mutex_base rtmutex; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; #define __MUTEX_INITIALIZER(mutexname) \ { \ diff --git a/include/linux/mutex_types.h b/include/linux/mutex_types.h new file mode 100644 index 000000000000..fdf7f515fde8 --- /dev/null +++ b/include/linux/mutex_types.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_MUTEX_TYPES_H +#define __LINUX_MUTEX_TYPES_H + +#include <linux/atomic.h> +#include <linux/lockdep_types.h> +#include <linux/osq_lock.h> +#include <linux/spinlock_types.h> +#include <linux/types.h> + +#ifndef CONFIG_PREEMPT_RT + +/* + * Simple, straightforward mutexes with strict semantics: + * + * - only one task can hold the mutex at a time + * - only the owner can unlock the mutex + * - multiple unlocks are not permitted + * - recursive locking is not permitted + * - a mutex object must be initialized via the API + * - a mutex object must not be initialized via memset or copying + * - task may not exit with mutex held + * - memory areas where held locks reside must not be freed + * - held mutexes must not be reinitialized + * - mutexes may not be used in hardware or software interrupt + * contexts such as tasklets and timers + * + * These semantics are fully enforced when DEBUG_MUTEXES is + * enabled. Furthermore, besides enforcing the above rules, the mutex + * debugging code also implements a number of additional features + * that make lock debugging easier and faster: + * + * - uses symbolic names of mutexes, whenever they are printed in debug output + * - point-of-acquire tracking, symbolic lookup of function names + * - list of all locks held in the system, printout of them + * - owner tracking + * - detects self-recursing locks and prints out all relevant info + * - detects multi-task circular deadlocks and prints out all affected + * locks and tasks (and only those tasks) + */ +struct mutex { + atomic_long_t owner; + raw_spinlock_t wait_lock; +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER + struct optimistic_spin_queue osq; /* Spinner MCS lock */ +#endif + struct list_head wait_list; +#ifdef CONFIG_DEBUG_MUTEXES + void *magic; +#endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#else /* !CONFIG_PREEMPT_RT */ +/* + * Preempt-RT variant based on rtmutexes. + */ +#include <linux/rtmutex.h> + +struct mutex { + struct rt_mutex_base rtmutex; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#endif /* CONFIG_PREEMPT_RT */ + +#endif /* __LINUX_MUTEX_TYPES_H */ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 8d07116caaf1..b61438313a73 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -93,10 +93,10 @@ #include <linux/threads.h> #include <linux/bitmap.h> #include <linux/minmax.h> +#include <linux/nodemask_types.h> #include <linux/numa.h> #include <linux/random.h> -typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; extern nodemask_t _unused_nodemask_arg_; /** diff --git a/include/linux/nodemask_types.h b/include/linux/nodemask_types.h new file mode 100644 index 000000000000..6b28d97ea6ed --- /dev/null +++ b/include/linux/nodemask_types.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_NODEMASK_TYPES_H +#define __LINUX_NODEMASK_TYPES_H + +#include <linux/bitops.h> +#include <linux/numa.h> + +typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; + +#endif /* __LINUX_NODEMASK_TYPES_H */ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 771cb0285872..5601d14e2886 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -2,6 +2,7 @@ #ifndef _LINUX_NSPROXY_H #define _LINUX_NSPROXY_H +#include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/sched.h> diff --git a/include/linux/numa.h b/include/linux/numa.h index a904861de800..915033a75731 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NUMA_H #define _LINUX_NUMA_H +#include <linux/init.h> #include <linux/types.h> #ifdef CONFIG_NODES_SHIFT @@ -22,34 +23,26 @@ #endif #ifdef CONFIG_NUMA -#include <linux/printk.h> #include <asm/sparsemem.h> /* Generic implementation available */ int numa_nearest_node(int node, unsigned int state); #ifndef memory_add_physaddr_to_nid -static inline int memory_add_physaddr_to_nid(u64 start) -{ - pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} +int memory_add_physaddr_to_nid(u64 start); #endif + #ifndef phys_to_target_node -static inline int phys_to_target_node(u64 start) -{ - pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} +int phys_to_target_node(u64 start); #endif + #ifndef numa_fill_memblks static inline int __init numa_fill_memblks(u64 start, u64 end) { return NUMA_NO_MEMBLK; } #endif + #else /* !CONFIG_NUMA */ static inline int numa_nearest_node(int node, unsigned int state) { diff --git a/include/linux/pid.h b/include/linux/pid.h index 653a527574c4..395cacce1179 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -2,18 +2,12 @@ #ifndef _LINUX_PID_H #define _LINUX_PID_H +#include <linux/pid_types.h> #include <linux/rculist.h> -#include <linux/wait.h> +#include <linux/rcupdate.h> #include <linux/refcount.h> - -enum pid_type -{ - PIDTYPE_PID, - PIDTYPE_TGID, - PIDTYPE_PGID, - PIDTYPE_SID, - PIDTYPE_MAX, -}; +#include <linux/sched.h> +#include <linux/wait.h> /* * What is struct pid? @@ -110,9 +104,6 @@ extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); -struct pid_namespace; -extern struct pid_namespace init_pid_ns; - extern int pid_max; extern int pid_max_min, pid_max_max; @@ -215,4 +206,127 @@ pid_t pid_vnr(struct pid *pid); } \ task = tg___; \ } while_each_pid_task(pid, type, task) + +static inline struct pid *task_pid(struct task_struct *task) +{ + return task->thread_pid; +} + +/* + * the helpers to get the task's different pids as they are seen + * from various namespaces + * + * task_xid_nr() : global id, i.e. the id seen from the init namespace; + * task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of + * current. + * task_xid_nr_ns() : id seen from the ns specified; + * + * see also pid_nr() etc in include/linux/pid.h + */ +pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); + +static inline pid_t task_pid_nr(struct task_struct *tsk) +{ + return tsk->pid; +} + +static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); +} + +static inline pid_t task_pid_vnr(struct task_struct *tsk) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); +} + + +static inline pid_t task_tgid_nr(struct task_struct *tsk) +{ + return tsk->tgid; +} + +/** + * pid_alive - check that a task structure is not stale + * @p: Task structure to be checked. + * + * Test if a process is not yet dead (at most zombie state) + * If pid_alive fails, then pointers within the task structure + * can be stale and must not be dereferenced. + * + * Return: 1 if the process is alive. 0 otherwise. + */ +static inline int pid_alive(const struct task_struct *p) +{ + return p->thread_pid != NULL; +} + +static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); +} + +static inline pid_t task_pgrp_vnr(struct task_struct *tsk) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); +} + + +static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); +} + +static inline pid_t task_session_vnr(struct task_struct *tsk) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); +} + +static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns); +} + +static inline pid_t task_tgid_vnr(struct task_struct *tsk) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL); +} + +static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) +{ + pid_t pid = 0; + + rcu_read_lock(); + if (pid_alive(tsk)) + pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); + rcu_read_unlock(); + + return pid; +} + +static inline pid_t task_ppid_nr(const struct task_struct *tsk) +{ + return task_ppid_nr_ns(tsk, &init_pid_ns); +} + +/* Obsolete, do not use: */ +static inline pid_t task_pgrp_nr(struct task_struct *tsk) +{ + return task_pgrp_nr_ns(tsk, &init_pid_ns); +} + +/** + * is_global_init - check if a task structure is init. Since init + * is free to have sub-threads we need to check tgid. + * @tsk: Task structure to be checked. + * + * Check if a task structure is the first user space task the kernel created. + * + * Return: 1 if the task structure is init. 0 otherwise. + */ +static inline int is_global_init(struct task_struct *tsk) +{ + return task_tgid_nr(tsk) == 1; +} + #endif /* _LINUX_PID_H */ diff --git a/include/linux/pid_types.h b/include/linux/pid_types.h new file mode 100644 index 000000000000..c2aee1d91dcf --- /dev/null +++ b/include/linux/pid_types.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PID_TYPES_H +#define _LINUX_PID_TYPES_H + +enum pid_type { + PIDTYPE_PID, + PIDTYPE_TGID, + PIDTYPE_PGID, + PIDTYPE_SID, + PIDTYPE_MAX, +}; + +struct pid_namespace; +extern struct pid_namespace init_pid_ns; + +#endif /* _LINUX_PID_TYPES_H */ diff --git a/include/linux/plist.h b/include/linux/plist.h index 0f352c1d3c80..8c1c8adf7fe9 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -75,20 +75,10 @@ #include <linux/container_of.h> #include <linux/list.h> -#include <linux/types.h> +#include <linux/plist_types.h> #include <asm/bug.h> -struct plist_head { - struct list_head node_list; -}; - -struct plist_node { - int prio; - struct list_head prio_list; - struct list_head node_list; -}; - /** * PLIST_HEAD_INIT - static struct plist_head initializer * @head: struct plist_head variable name diff --git a/include/linux/plist_types.h b/include/linux/plist_types.h new file mode 100644 index 000000000000..c37e784330af --- /dev/null +++ b/include/linux/plist_types.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_PLIST_TYPES_H +#define _LINUX_PLIST_TYPES_H + +#include <linux/types.h> + +struct plist_head { + struct list_head node_list; +}; + +struct plist_node { + int prio; + struct list_head prio_list; + struct list_head node_list; +}; + +#endif /* _LINUX_PLIST_TYPES_H */ diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index d607f51404fc..dc7b738de299 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -2,40 +2,16 @@ #ifndef _linux_POSIX_TIMERS_H #define _linux_POSIX_TIMERS_H -#include <linux/spinlock.h> +#include <linux/alarmtimer.h> #include <linux/list.h> #include <linux/mutex.h> -#include <linux/alarmtimer.h> +#include <linux/posix-timers_types.h> +#include <linux/spinlock.h> #include <linux/timerqueue.h> struct kernel_siginfo; struct task_struct; -/* - * Bit fields within a clockid: - * - * The most significant 29 bits hold either a pid or a file descriptor. - * - * Bit 2 indicates whether a cpu clock refers to a thread or a process. - * - * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3. - * - * A clockid is invalid if bits 2, 1, and 0 are all set. - */ -#define CPUCLOCK_PID(clock) ((pid_t) ~((clock) >> 3)) -#define CPUCLOCK_PERTHREAD(clock) \ - (((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0) - -#define CPUCLOCK_PERTHREAD_MASK 4 -#define CPUCLOCK_WHICH(clock) ((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK) -#define CPUCLOCK_CLOCK_MASK 3 -#define CPUCLOCK_PROF 0 -#define CPUCLOCK_VIRT 1 -#define CPUCLOCK_SCHED 2 -#define CPUCLOCK_MAX 3 -#define CLOCKFD CPUCLOCK_MAX -#define CLOCKFD_MASK (CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK) - static inline clockid_t make_process_cpuclock(const unsigned int pid, const clockid_t clock) { @@ -109,44 +85,6 @@ static inline void cpu_timer_setexpires(struct cpu_timer *ctmr, u64 exp) ctmr->node.expires = exp; } -/** - * posix_cputimer_base - Container per posix CPU clock - * @nextevt: Earliest-expiration cache - * @tqhead: timerqueue head for cpu_timers - */ -struct posix_cputimer_base { - u64 nextevt; - struct timerqueue_head tqhead; -}; - -/** - * posix_cputimers - Container for posix CPU timer related data - * @bases: Base container for posix CPU clocks - * @timers_active: Timers are queued. - * @expiry_active: Timer expiry is active. Used for - * process wide timers to avoid multiple - * task trying to handle expiry concurrently - * - * Used in task_struct and signal_struct - */ -struct posix_cputimers { - struct posix_cputimer_base bases[CPUCLOCK_MAX]; - unsigned int timers_active; - unsigned int expiry_active; -}; - -/** - * posix_cputimers_work - Container for task work based posix CPU timer expiry - * @work: The task work to be scheduled - * @mutex: Mutex held around expiry in context of this task work - * @scheduled: @work has been scheduled already, no further processing - */ -struct posix_cputimers_work { - struct callback_head work; - struct mutex mutex; - unsigned int scheduled; -}; - static inline void posix_cputimers_init(struct posix_cputimers *pct) { memset(pct, 0, sizeof(*pct)); @@ -179,7 +117,6 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, .bases = INIT_CPU_TIMERBASES(s.posix_cputimers.bases), \ }, #else -struct posix_cputimers { }; struct cpu_timer { }; #define INIT_CPU_TIMERS(s) static inline void posix_cputimers_init(struct posix_cputimers *pct) { } diff --git a/include/linux/posix-timers_types.h b/include/linux/posix-timers_types.h new file mode 100644 index 000000000000..a4712c1008c9 --- /dev/null +++ b/include/linux/posix-timers_types.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _linux_POSIX_TIMERS_TYPES_H +#define _linux_POSIX_TIMERS_TYPES_H + +#include <linux/mutex_types.h> +#include <linux/timerqueue_types.h> +#include <linux/types.h> + +/* + * Bit fields within a clockid: + * + * The most significant 29 bits hold either a pid or a file descriptor. + * + * Bit 2 indicates whether a cpu clock refers to a thread or a process. + * + * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3. + * + * A clockid is invalid if bits 2, 1, and 0 are all set. + */ +#define CPUCLOCK_PID(clock) ((pid_t) ~((clock) >> 3)) +#define CPUCLOCK_PERTHREAD(clock) \ + (((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0) + +#define CPUCLOCK_PERTHREAD_MASK 4 +#define CPUCLOCK_WHICH(clock) ((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK) +#define CPUCLOCK_CLOCK_MASK 3 +#define CPUCLOCK_PROF 0 +#define CPUCLOCK_VIRT 1 +#define CPUCLOCK_SCHED 2 +#define CPUCLOCK_MAX 3 +#define CLOCKFD CPUCLOCK_MAX +#define CLOCKFD_MASK (CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK) + +#ifdef CONFIG_POSIX_TIMERS + +/** + * posix_cputimer_base - Container per posix CPU clock + * @nextevt: Earliest-expiration cache + * @tqhead: timerqueue head for cpu_timers + */ +struct posix_cputimer_base { + u64 nextevt; + struct timerqueue_head tqhead; +}; + +/** + * posix_cputimers - Container for posix CPU timer related data + * @bases: Base container for posix CPU clocks + * @timers_active: Timers are queued. + * @expiry_active: Timer expiry is active. Used for + * process wide timers to avoid multiple + * task trying to handle expiry concurrently + * + * Used in task_struct and signal_struct + */ +struct posix_cputimers { + struct posix_cputimer_base bases[CPUCLOCK_MAX]; + unsigned int timers_active; + unsigned int expiry_active; +}; + +/** + * posix_cputimers_work - Container for task work based posix CPU timer expiry + * @work: The task work to be scheduled + * @mutex: Mutex held around expiry in context of this task work + * @scheduled: @work has been scheduled already, no further processing + */ +struct posix_cputimers_work { + struct callback_head work; + struct mutex mutex; + unsigned int scheduled; +}; + +#else /* CONFIG_POSIX_TIMERS */ + +struct posix_cputimers { }; + +#endif /* CONFIG_POSIX_TIMERS */ + +#endif /* _linux_POSIX_TIMERS_TYPES_H */ diff --git a/include/linux/prandom.h b/include/linux/prandom.h index f2ed5b72b3d6..f7f1e5251c67 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -10,7 +10,6 @@ #include <linux/types.h> #include <linux/once.h> -#include <linux/percpu.h> #include <linux/random.h> struct rnd_state { diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 9aa6358a1a16..7233e9cf1bab 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -9,7 +9,7 @@ #include <linux/linkage.h> #include <linux/cleanup.h> -#include <linux/list.h> +#include <linux/types.h> /* * We put the hardirq and softirq counter into the preemption @@ -360,7 +360,9 @@ void preempt_notifier_unregister(struct preempt_notifier *notifier); static inline void preempt_notifier_init(struct preempt_notifier *notifier, struct preempt_ops *ops) { - INIT_HLIST_NODE(¬ifier->link); + /* INIT_HLIST_NODE() open coded, to avoid dependency on list.h */ + notifier->link.next = NULL; + notifier->link.pprev = NULL; notifier->ops = ops; } diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index 5e0f74f2f8ca..d07f0848802e 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -8,6 +8,7 @@ #include <linux/rcupdate.h> #include <linux/completion.h> +#include <linux/sched.h> /* * Structure allowing asynchronous waiting on RCU. @@ -55,4 +56,13 @@ do { \ #define synchronize_rcu_mult(...) \ _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) +static inline void cond_resched_rcu(void) +{ +#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU) + rcu_read_unlock(); + cond_resched(); + rcu_read_lock(); +#endif +} + #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */ diff --git a/include/linux/refcount.h b/include/linux/refcount.h index a62fcca97486..85c6df0d1bef 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -96,22 +96,11 @@ #include <linux/bug.h> #include <linux/compiler.h> #include <linux/limits.h> +#include <linux/refcount_types.h> #include <linux/spinlock_types.h> struct mutex; -/** - * typedef refcount_t - variant of atomic_t specialized for reference counts - * @refs: atomic_t counter field - * - * The counter saturates at REFCOUNT_SATURATED and will not move once - * there. This avoids wrapping the counter and causing 'spurious' - * use-after-free bugs. - */ -typedef struct refcount_struct { - atomic_t refs; -} refcount_t; - #define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } #define REFCOUNT_MAX INT_MAX #define REFCOUNT_SATURATED (INT_MIN / 2) diff --git a/include/linux/refcount_types.h b/include/linux/refcount_types.h new file mode 100644 index 000000000000..162004f06edf --- /dev/null +++ b/include/linux/refcount_types.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_REFCOUNT_TYPES_H +#define _LINUX_REFCOUNT_TYPES_H + +#include <linux/types.h> + +/** + * typedef refcount_t - variant of atomic_t specialized for reference counts + * @refs: atomic_t counter field + * + * The counter saturates at REFCOUNT_SATURATED and will not move once + * there. This avoids wrapping the counter and causing 'spurious' + * use-after-free bugs. + */ +typedef struct refcount_struct { + atomic_t refs; +} refcount_t; + +#endif /* _LINUX_REFCOUNT_TYPES_H */ diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h index 980a65594412..13f17676c5f4 100644 --- a/include/linux/restart_block.h +++ b/include/linux/restart_block.h @@ -7,8 +7,8 @@ #include <linux/compiler.h> #include <linux/types.h> -#include <linux/time64.h> +struct __kernel_timespec; struct timespec; struct old_timespec32; struct pollfd; diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h index f8f3e958e9cf..e0135e0adae0 100644 --- a/include/linux/resume_user_mode.h +++ b/include/linux/resume_user_mode.h @@ -6,6 +6,7 @@ #include <linux/sched.h> #include <linux/task_work.h> #include <linux/memcontrol.h> +#include <linux/rseq.h> #include <linux/blk-cgroup.h> /** diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h index 57467cbf4c5b..b6f3797277ff 100644 --- a/include/linux/rhashtable-types.h +++ b/include/linux/rhashtable-types.h @@ -12,7 +12,7 @@ #include <linux/atomic.h> #include <linux/compiler.h> #include <linux/mutex.h> -#include <linux/workqueue.h> +#include <linux/workqueue_types.h> struct rhash_head { struct rhash_head __rcu *next; diff --git a/include/linux/rseq.h b/include/linux/rseq.h new file mode 100644 index 000000000000..bc8af3eb5598 --- /dev/null +++ b/include/linux/rseq.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +#ifndef _LINUX_RSEQ_H +#define _LINUX_RSEQ_H + +#ifdef CONFIG_RSEQ + +#include <linux/preempt.h> +#include <linux/sched.h> + +/* + * Map the event mask on the user-space ABI enum rseq_cs_flags + * for direct mask checks. + */ +enum rseq_event_mask_bits { + RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, + RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, + RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, +}; + +enum rseq_event_mask { + RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), + RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), + RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), +}; + +static inline void rseq_set_notify_resume(struct task_struct *t) +{ + if (t->rseq) + set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); +} + +void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); + +static inline void rseq_handle_notify_resume(struct ksignal *ksig, + struct pt_regs *regs) +{ + if (current->rseq) + __rseq_handle_notify_resume(ksig, regs); +} + +static inline void rseq_signal_deliver(struct ksignal *ksig, + struct pt_regs *regs) +{ + preempt_disable(); + __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); + preempt_enable(); + rseq_handle_notify_resume(ksig, regs); +} + +/* rseq_preempt() requires preemption to be disabled. */ +static inline void rseq_preempt(struct task_struct *t) +{ + __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); + rseq_set_notify_resume(t); +} + +/* rseq_migrate() requires preemption to be disabled. */ +static inline void rseq_migrate(struct task_struct *t) +{ + __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); + rseq_set_notify_resume(t); +} + +/* + * If parent process has a registered restartable sequences area, the + * child inherits. Unregister rseq for a clone with CLONE_VM set. + */ +static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) +{ + if (clone_flags & CLONE_VM) { + t->rseq = NULL; + t->rseq_len = 0; + t->rseq_sig = 0; + t->rseq_event_mask = 0; + } else { + t->rseq = current->rseq; + t->rseq_len = current->rseq_len; + t->rseq_sig = current->rseq_sig; + t->rseq_event_mask = current->rseq_event_mask; + } +} + +static inline void rseq_execve(struct task_struct *t) +{ + t->rseq = NULL; + t->rseq_len = 0; + t->rseq_sig = 0; + t->rseq_event_mask = 0; +} + +#else + +static inline void rseq_set_notify_resume(struct task_struct *t) +{ +} +static inline void rseq_handle_notify_resume(struct ksignal *ksig, + struct pt_regs *regs) +{ +} +static inline void rseq_signal_deliver(struct ksignal *ksig, + struct pt_regs *regs) +{ +} +static inline void rseq_preempt(struct task_struct *t) +{ +} +static inline void rseq_migrate(struct task_struct *t) +{ +} +static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) +{ +} +static inline void rseq_execve(struct task_struct *t) +{ +} + +#endif + +#ifdef CONFIG_DEBUG_RSEQ + +void rseq_syscall(struct pt_regs *regs); + +#else + +static inline void rseq_syscall(struct pt_regs *regs) +{ +} + +#endif + +#endif /* _LINUX_RSEQ_H */ diff --git a/include/linux/rslib.h b/include/linux/rslib.h index 238bb85243d3..a04dacbdc8ae 100644 --- a/include/linux/rslib.h +++ b/include/linux/rslib.h @@ -10,7 +10,6 @@ #ifndef _RSLIB_H_ #define _RSLIB_H_ -#include <linux/list.h> #include <linux/types.h> /* for gfp_t */ #include <linux/gfp.h> /* for GFP_KERNEL */ diff --git a/include/linux/sched.h b/include/linux/sched.h index d3097f0682d7..9a66147915b2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -10,33 +10,41 @@ #include <uapi/linux/sched.h> #include <asm/current.h> - -#include <linux/pid.h> -#include <linux/sem.h> +#include <asm/processor.h> +#include <linux/thread_info.h> +#include <linux/preempt.h> +#include <linux/cpumask.h> + +#include <linux/cache.h> +#include <linux/irqflags_types.h> +#include <linux/smp_types.h> +#include <linux/pid_types.h> +#include <linux/sem_types.h> #include <linux/shm.h> #include <linux/kmsan_types.h> -#include <linux/mutex.h> -#include <linux/plist.h> -#include <linux/hrtimer.h> -#include <linux/irqflags.h> -#include <linux/seccomp.h> -#include <linux/nodemask.h> -#include <linux/rcupdate.h> -#include <linux/refcount.h> +#include <linux/mutex_types.h> +#include <linux/plist_types.h> +#include <linux/hrtimer_types.h> +#include <linux/timer_types.h> +#include <linux/seccomp_types.h> +#include <linux/nodemask_types.h> +#include <linux/refcount_types.h> #include <linux/resource.h> #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/sched/types.h> #include <linux/signal_types.h> -#include <linux/syscall_user_dispatch.h> +#include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> #include <linux/task_io_accounting.h> -#include <linux/posix-timers.h> -#include <linux/rseq.h> -#include <linux/seqlock.h> +#include <linux/posix-timers_types.h> +#include <linux/restart_block.h> +#include <uapi/linux/rseq.h> +#include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> #include <linux/livepatch_sched.h> +#include <linux/uidgid_types.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ @@ -1556,114 +1564,6 @@ struct task_struct { */ }; -static inline struct pid *task_pid(struct task_struct *task) -{ - return task->thread_pid; -} - -/* - * the helpers to get the task's different pids as they are seen - * from various namespaces - * - * task_xid_nr() : global id, i.e. the id seen from the init namespace; - * task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of - * current. - * task_xid_nr_ns() : id seen from the ns specified; - * - * see also pid_nr() etc in include/linux/pid.h - */ -pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); - -static inline pid_t task_pid_nr(struct task_struct *tsk) -{ - return tsk->pid; -} - -static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); -} - -static inline pid_t task_pid_vnr(struct task_struct *tsk) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); -} - - -static inline pid_t task_tgid_nr(struct task_struct *tsk) -{ - return tsk->tgid; -} - -/** - * pid_alive - check that a task structure is not stale - * @p: Task structure to be checked. - * - * Test if a process is not yet dead (at most zombie state) - * If pid_alive fails, then pointers within the task structure - * can be stale and must not be dereferenced. - * - * Return: 1 if the process is alive. 0 otherwise. - */ -static inline int pid_alive(const struct task_struct *p) -{ - return p->thread_pid != NULL; -} - -static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); -} - -static inline pid_t task_pgrp_vnr(struct task_struct *tsk) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); -} - - -static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); -} - -static inline pid_t task_session_vnr(struct task_struct *tsk) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); -} - -static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns); -} - -static inline pid_t task_tgid_vnr(struct task_struct *tsk) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL); -} - -static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) -{ - pid_t pid = 0; - - rcu_read_lock(); - if (pid_alive(tsk)) - pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); - rcu_read_unlock(); - - return pid; -} - -static inline pid_t task_ppid_nr(const struct task_struct *tsk) -{ - return task_ppid_nr_ns(tsk, &init_pid_ns); -} - -/* Obsolete, do not use: */ -static inline pid_t task_pgrp_nr(struct task_struct *tsk) -{ - return task_pgrp_nr_ns(tsk, &init_pid_ns); -} - #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) @@ -1707,20 +1607,6 @@ static inline char task_state_to_char(struct task_struct *tsk) return task_index_to_char(task_state_index(tsk)); } -/** - * is_global_init - check if a task structure is init. Since init - * is free to have sub-threads we need to check tgid. - * @tsk: Task structure to be checked. - * - * Check if a task structure is the first user space task the kernel created. - * - * Return: 1 if the task structure is init. 0 otherwise. - */ -static inline int is_global_init(struct task_struct *tsk) -{ - return task_tgid_nr(tsk) == 1; -} - extern struct pid *cad_pid; /* @@ -2170,15 +2056,6 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock); __cond_resched_rwlock_write(lock); \ }) -static inline void cond_resched_rcu(void) -{ -#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU) - rcu_read_unlock(); - cond_resched(); - rcu_read_lock(); -#endif -} - #ifdef CONFIG_PREEMPT_DYNAMIC extern bool preempt_model_none(void); @@ -2220,37 +2097,6 @@ static inline bool preempt_model_preemptible(void) return preempt_model_full() || preempt_model_rt(); } -/* - * Does a critical section need to be broken due to another - * task waiting?: (technically does not depend on CONFIG_PREEMPTION, - * but a general need for low latency) - */ -static inline int spin_needbreak(spinlock_t *lock) -{ -#ifdef CONFIG_PREEMPTION - return spin_is_contended(lock); -#else - return 0; -#endif -} - -/* - * Check if a rwlock is contended. - * Returns non-zero if there is another task waiting on the rwlock. - * Returns zero if the lock is not contended or the system / underlying - * rwlock implementation does not support contention detection. - * Technically does not depend on CONFIG_PREEMPTION, but a general need - * for low latency. - */ -static inline int rwlock_needbreak(rwlock_t *lock) -{ -#ifdef CONFIG_PREEMPTION - return rwlock_is_contended(lock); -#else - return 0; -#endif -} - static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); @@ -2285,6 +2131,8 @@ extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_curr_snapshot(int cpu); +#include <linux/spinlock.h> + /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. @@ -2321,129 +2169,6 @@ static inline bool owner_on_cpu(struct task_struct *owner) unsigned long sched_cpu_util(int cpu); #endif /* CONFIG_SMP */ -#ifdef CONFIG_RSEQ - -/* - * Map the event mask on the user-space ABI enum rseq_cs_flags - * for direct mask checks. - */ -enum rseq_event_mask_bits { - RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, - RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, - RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, -}; - -enum rseq_event_mask { - RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), - RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), - RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), -}; - -static inline void rseq_set_notify_resume(struct task_struct *t) -{ - if (t->rseq) - set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); -} - -void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); - -static inline void rseq_handle_notify_resume(struct ksignal *ksig, - struct pt_regs *regs) -{ - if (current->rseq) - __rseq_handle_notify_resume(ksig, regs); -} - -static inline void rseq_signal_deliver(struct ksignal *ksig, - struct pt_regs *regs) -{ - preempt_disable(); - __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); - preempt_enable(); - rseq_handle_notify_resume(ksig, regs); -} - -/* rseq_preempt() requires preemption to be disabled. */ -static inline void rseq_preempt(struct task_struct *t) -{ - __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); - rseq_set_notify_resume(t); -} - -/* rseq_migrate() requires preemption to be disabled. */ -static inline void rseq_migrate(struct task_struct *t) -{ - __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); - rseq_set_notify_resume(t); -} - -/* - * If parent process has a registered restartable sequences area, the - * child inherits. Unregister rseq for a clone with CLONE_VM set. - */ -static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) -{ - if (clone_flags & CLONE_VM) { - t->rseq = NULL; - t->rseq_len = 0; - t->rseq_sig = 0; - t->rseq_event_mask = 0; - } else { - t->rseq = current->rseq; - t->rseq_len = current->rseq_len; - t->rseq_sig = current->rseq_sig; - t->rseq_event_mask = current->rseq_event_mask; - } -} - -static inline void rseq_execve(struct task_struct *t) -{ - t->rseq = NULL; - t->rseq_len = 0; - t->rseq_sig = 0; - t->rseq_event_mask = 0; -} - -#else - -static inline void rseq_set_notify_resume(struct task_struct *t) -{ -} -static inline void rseq_handle_notify_resume(struct ksignal *ksig, - struct pt_regs *regs) -{ -} -static inline void rseq_signal_deliver(struct ksignal *ksig, - struct pt_regs *regs) -{ -} -static inline void rseq_preempt(struct task_struct *t) -{ -} -static inline void rseq_migrate(struct task_struct *t) -{ -} -static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) -{ -} -static inline void rseq_execve(struct task_struct *t) -{ -} - -#endif - -#ifdef CONFIG_DEBUG_RSEQ - -void rseq_syscall(struct pt_regs *regs); - -#else - -static inline void rseq_syscall(struct pt_regs *regs) -{ -} - -#endif - #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 015c0e3a3e1d..4b7664c56208 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -9,6 +9,7 @@ #include <linux/sched/task.h> #include <linux/cred.h> #include <linux/refcount.h> +#include <linux/pid.h> #include <linux/posix-timers.h> #include <linux/mm_types.h> #include <asm/ptrace.h> diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 4f3dca353556..d362aacf9f89 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -7,6 +7,8 @@ * functionality: */ +#include <linux/rcupdate.h> +#include <linux/refcount.h> #include <linux/sched.h> #include <linux/uaccess.h> diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index f158b025c175..ccd72b978e1f 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -8,6 +8,7 @@ #include <linux/sched.h> #include <linux/magic.h> +#include <linux/refcount.h> #ifdef CONFIG_THREAD_INFO_IN_TASK diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 175079552f68..709ad84809e1 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -3,6 +3,7 @@ #define _LINUX_SECCOMP_H #include <uapi/linux/seccomp.h> +#include <linux/seccomp_types.h> #define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ SECCOMP_FILTER_FLAG_LOG | \ @@ -21,25 +22,6 @@ #include <linux/atomic.h> #include <asm/seccomp.h> -struct seccomp_filter; -/** - * struct seccomp - the state of a seccomp'ed process - * - * @mode: indicates one of the valid values above for controlled - * system calls available to a process. - * @filter_count: number of seccomp filters - * @filter: must always point to a valid seccomp-filter or NULL as it is - * accessed without locking during system call entry. - * - * @filter must only be accessed from the context of current as there - * is no read locking. - */ -struct seccomp { - int mode; - atomic_t filter_count; - struct seccomp_filter *filter; -}; - #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER extern int __secure_computing(const struct seccomp_data *sd); static inline int secure_computing(void) @@ -64,8 +46,6 @@ static inline int seccomp_mode(struct seccomp *s) #include <linux/errno.h> -struct seccomp { }; -struct seccomp_filter { }; struct seccomp_data; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER @@ -126,6 +106,8 @@ static inline long seccomp_get_metadata(struct task_struct *task, #ifdef CONFIG_SECCOMP_CACHE_DEBUG struct seq_file; +struct pid_namespace; +struct pid; int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task); diff --git a/include/linux/seccomp_types.h b/include/linux/seccomp_types.h new file mode 100644 index 000000000000..cf0a0355024f --- /dev/null +++ b/include/linux/seccomp_types.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SECCOMP_TYPES_H +#define _LINUX_SECCOMP_TYPES_H + +#include <linux/types.h> + +#ifdef CONFIG_SECCOMP + +struct seccomp_filter; +/** + * struct seccomp - the state of a seccomp'ed process + * + * @mode: indicates one of the valid values above for controlled + * system calls available to a process. + * @filter_count: number of seccomp filters + * @filter: must always point to a valid seccomp-filter or NULL as it is + * accessed without locking during system call entry. + * + * @filter must only be accessed from the context of current as there + * is no read locking. + */ +struct seccomp { + int mode; + atomic_t filter_count; + struct seccomp_filter *filter; +}; + +#else + +struct seccomp { }; +struct seccomp_filter { }; + +#endif + +#endif /* _LINUX_SECCOMP_TYPES_H */ diff --git a/include/linux/sem.h b/include/linux/sem.h index 5608a500c43e..c4deefe42aeb 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -3,25 +3,17 @@ #define _LINUX_SEM_H #include <uapi/linux/sem.h> +#include <linux/sem_types.h> struct task_struct; -struct sem_undo_list; #ifdef CONFIG_SYSVIPC -struct sysv_sem { - struct sem_undo_list *undo_list; -}; - extern int copy_semundo(unsigned long clone_flags, struct task_struct *tsk); extern void exit_sem(struct task_struct *tsk); #else -struct sysv_sem { - /* empty */ -}; - static inline int copy_semundo(unsigned long clone_flags, struct task_struct *tsk) { return 0; diff --git a/include/linux/sem_types.h b/include/linux/sem_types.h new file mode 100644 index 000000000000..73df1971a7ae --- /dev/null +++ b/include/linux/sem_types.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SEM_TYPES_H +#define _LINUX_SEM_TYPES_H + +struct sem_undo_list; + +struct sysv_sem { +#ifdef CONFIG_SYSVIPC + struct sem_undo_list *undo_list; +#endif +}; + +#endif /* _LINUX_SEM_TYPES_H */ diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index e92f9d5577ba..d90d8ee29d81 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -18,6 +18,7 @@ #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/preempt.h> +#include <linux/seqlock_types.h> #include <linux/spinlock.h> #include <asm/processor.h> @@ -37,37 +38,6 @@ */ #define KCSAN_SEQLOCK_REGION_MAX 1000 -/* - * Sequence counters (seqcount_t) - * - * This is the raw counting mechanism, without any writer protection. - * - * Write side critical sections must be serialized and non-preemptible. - * - * If readers can be invoked from hardirq or softirq contexts, - * interrupts or bottom halves must also be respectively disabled before - * entering the write section. - * - * This mechanism can't be used if the protected data contains pointers, - * as the writer can invalidate a pointer that a reader is following. - * - * If the write serialization mechanism is one of the common kernel - * locking primitives, use a sequence counter with associated lock - * (seqcount_LOCKNAME_t) instead. - * - * If it's desired to automatically handle the sequence counter writer - * serialization and non-preemptibility requirements, use a sequential - * lock (seqlock_t) instead. - * - * See Documentation/locking/seqlock.rst - */ -typedef struct seqcount { - unsigned sequence; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -} seqcount_t; - static inline void __seqcount_init(seqcount_t *s, const char *name, struct lock_class_key *key) { @@ -132,28 +102,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) */ /* - * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot - * disable preemption. It can lead to higher latencies, and the write side - * sections will not be able to acquire locks which become sleeping locks - * (e.g. spinlock_t). - * - * To remain preemptible while avoiding a possible livelock caused by the - * reader preempting the writer, use a different technique: let the reader - * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the - * case, acquire then release the associated LOCKNAME writer serialization - * lock. This will allow any possibly-preempted writer to make progress - * until the end of its writer serialization lock critical section. - * - * This lock-unlock technique must be implemented for all of PREEMPT_RT - * sleeping locks. See Documentation/locking/locktypes.rst - */ -#if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT) -#define __SEQ_LOCK(expr) expr -#else -#define __SEQ_LOCK(expr) -#endif - -/* * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated * @seqcount: The real sequence counter * @lock: Pointer to the associated lock @@ -194,11 +142,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) * @lockbase: prefix for associated lock/unlock */ #define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase) \ -typedef struct seqcount_##lockname { \ - seqcount_t seqcount; \ - __SEQ_LOCK(locktype *lock); \ -} seqcount_##lockname##_t; \ - \ static __always_inline seqcount_t * \ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ @@ -284,6 +227,7 @@ SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, raw_spin) SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, spin) SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, read) SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) +#undef SEQCOUNT_LOCKNAME /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t @@ -794,25 +738,6 @@ static inline void raw_write_seqcount_latch(seqcount_latch_t *s) smp_wmb(); /* increment "sequence" before following stores */ } -/* - * Sequential locks (seqlock_t) - * - * Sequence counters with an embedded spinlock for writer serialization - * and non-preemptibility. - * - * For more info, see: - * - Comments on top of seqcount_t - * - Documentation/locking/seqlock.rst - */ -typedef struct { - /* - * Make sure that readers don't starve writers on PREEMPT_RT: use - * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK(). - */ - seqcount_spinlock_t seqcount; - spinlock_t lock; -} seqlock_t; - #define __SEQLOCK_UNLOCKED(lockname) \ { \ .seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \ diff --git a/include/linux/seqlock_types.h b/include/linux/seqlock_types.h new file mode 100644 index 000000000000..dfdf43e3fa3d --- /dev/null +++ b/include/linux/seqlock_types.h @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_SEQLOCK_TYPES_H +#define __LINUX_SEQLOCK_TYPES_H + +#include <linux/lockdep_types.h> +#include <linux/mutex_types.h> +#include <linux/spinlock_types.h> + +/* + * Sequence counters (seqcount_t) + * + * This is the raw counting mechanism, without any writer protection. + * + * Write side critical sections must be serialized and non-preemptible. + * + * If readers can be invoked from hardirq or softirq contexts, + * interrupts or bottom halves must also be respectively disabled before + * entering the write section. + * + * This mechanism can't be used if the protected data contains pointers, + * as the writer can invalidate a pointer that a reader is following. + * + * If the write serialization mechanism is one of the common kernel + * locking primitives, use a sequence counter with associated lock + * (seqcount_LOCKNAME_t) instead. + * + * If it's desired to automatically handle the sequence counter writer + * serialization and non-preemptibility requirements, use a sequential + * lock (seqlock_t) instead. + * + * See Documentation/locking/seqlock.rst + */ +typedef struct seqcount { + unsigned sequence; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} seqcount_t; + +/* + * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot + * disable preemption. It can lead to higher latencies, and the write side + * sections will not be able to acquire locks which become sleeping locks + * (e.g. spinlock_t). + * + * To remain preemptible while avoiding a possible livelock caused by the + * reader preempting the writer, use a different technique: let the reader + * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the + * case, acquire then release the associated LOCKNAME writer serialization + * lock. This will allow any possibly-preempted writer to make progress + * until the end of its writer serialization lock critical section. + * + * This lock-unlock technique must be implemented for all of PREEMPT_RT + * sleeping locks. See Documentation/locking/locktypes.rst + */ +#if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT) +#define __SEQ_LOCK(expr) expr +#else +#define __SEQ_LOCK(expr) +#endif + +#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase) \ +typedef struct seqcount_##lockname { \ + seqcount_t seqcount; \ + __SEQ_LOCK(locktype *lock); \ +} seqcount_##lockname##_t; + +SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, raw_spin) +SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, spin) +SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, read) +SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) +#undef SEQCOUNT_LOCKNAME + +/* + * Sequential locks (seqlock_t) + * + * Sequence counters with an embedded spinlock for writer serialization + * and non-preemptibility. + * + * For more info, see: + * - Comments on top of seqcount_t + * - Documentation/locking/seqlock.rst + */ +typedef struct { + /* + * Make sure that readers don't starve writers on PREEMPT_RT: use + * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK(). + */ + seqcount_spinlock_t seqcount; + spinlock_t lock; +} seqlock_t; + +#endif /* __LINUX_SEQLOCK_TYPES_H */ diff --git a/include/linux/shm.h b/include/linux/shm.h index d8e69aed3d32..c55bef0538e5 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -2,12 +2,12 @@ #ifndef _LINUX_SHM_H_ #define _LINUX_SHM_H_ -#include <linux/list.h> +#include <linux/types.h> #include <asm/page.h> -#include <uapi/linux/shm.h> #include <asm/shmparam.h> struct file; +struct task_struct; #ifdef CONFIG_SYSVIPC struct sysv_shm { diff --git a/include/linux/signal.h b/include/linux/signal.h index 3b98e7a28538..f19816832f05 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -3,6 +3,7 @@ #define _LINUX_SIGNAL_H #include <linux/bug.h> +#include <linux/list.h> #include <linux/signal_types.h> #include <linux/string.h> diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index a70b2bdbf4d9..caf4f7a59ab9 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -6,7 +6,7 @@ * Basic signal handling related data type definitions: */ -#include <linux/list.h> +#include <linux/types.h> #include <uapi/linux/signal.h> typedef struct kernel_siginfo { diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 90bc853cafb6..eaac8b0da25b 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -449,6 +449,37 @@ static __always_inline int spin_is_contended(spinlock_t *lock) return raw_spin_is_contended(&lock->rlock); } +/* + * Does a critical section need to be broken due to another + * task waiting?: (technically does not depend on CONFIG_PREEMPTION, + * but a general need for low latency) + */ +static inline int spin_needbreak(spinlock_t *lock) +{ +#ifdef CONFIG_PREEMPTION + return spin_is_contended(lock); +#else + return 0; +#endif +} + +/* + * Check if a rwlock is contended. + * Returns non-zero if there is another task waiting on the rwlock. + * Returns zero if the lock is not contended or the system / underlying + * rwlock implementation does not support contention detection. + * Technically does not depend on CONFIG_PREEMPTION, but a general need + * for low latency. + */ +static inline int rwlock_needbreak(rwlock_t *lock) +{ +#ifdef CONFIG_PREEMPTION + return rwlock_is_contended(lock); +#else + return 0; +#endif +} + #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) #else /* !CONFIG_PREEMPT_RT */ diff --git a/include/linux/syscall_user_dispatch.h b/include/linux/syscall_user_dispatch.h index 641ca8880995..3858a6ffdd5c 100644 --- a/include/linux/syscall_user_dispatch.h +++ b/include/linux/syscall_user_dispatch.h @@ -6,16 +6,10 @@ #define _SYSCALL_USER_DISPATCH_H #include <linux/thread_info.h> +#include <linux/syscall_user_dispatch_types.h> #ifdef CONFIG_GENERIC_ENTRY -struct syscall_user_dispatch { - char __user *selector; - unsigned long offset; - unsigned long len; - bool on_dispatch; -}; - int set_syscall_user_dispatch(unsigned long mode, unsigned long offset, unsigned long len, char __user *selector); @@ -29,7 +23,6 @@ int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long siz void __user *data); #else -struct syscall_user_dispatch {}; static inline int set_syscall_user_dispatch(unsigned long mode, unsigned long offset, unsigned long len, char __user *selector) diff --git a/include/linux/syscall_user_dispatch_types.h b/include/linux/syscall_user_dispatch_types.h new file mode 100644 index 000000000000..3be36b06c7d7 --- /dev/null +++ b/include/linux/syscall_user_dispatch_types.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _SYSCALL_USER_DISPATCH_TYPES_H +#define _SYSCALL_USER_DISPATCH_TYPES_H + +#include <linux/types.h> + +#ifdef CONFIG_GENERIC_ENTRY + +struct syscall_user_dispatch { + char __user *selector; + unsigned long offset; + unsigned long len; + bool on_dispatch; +}; + +#else + +struct syscall_user_dispatch {}; + +#endif + +#endif /* _SYSCALL_USER_DISPATCH_TYPES_H */ diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index 03d9c5ac01d1..876e31b4461d 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -7,10 +7,13 @@ #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/err.h> +#include <linux/time64.h> struct user_namespace; extern struct user_namespace init_user_ns; +struct vm_area_struct; + struct timens_offsets { struct timespec64 monotonic; struct timespec64 boottime; diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index fe1e467ba046..7c43e98cf211 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -4,6 +4,7 @@ #include <linux/errno.h> #include <linux/clocksource_ids.h> +#include <linux/ktime.h> /* Included from linux/ktime.h */ diff --git a/include/linux/timer.h b/include/linux/timer.h index 26a545bb0153..f18a2f1eb79e 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -7,21 +7,7 @@ #include <linux/stddef.h> #include <linux/debugobjects.h> #include <linux/stringify.h> - -struct timer_list { - /* - * All fields that change during normal runtime grouped to the - * same cacheline - */ - struct hlist_node entry; - unsigned long expires; - void (*function)(struct timer_list *); - u32 flags; - -#ifdef CONFIG_LOCKDEP - struct lockdep_map lockdep_map; -#endif -}; +#include <linux/timer_types.h> #ifdef CONFIG_LOCKDEP /* diff --git a/include/linux/timer_types.h b/include/linux/timer_types.h new file mode 100644 index 000000000000..fae5a388f914 --- /dev/null +++ b/include/linux/timer_types.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TIMER_TYPES_H +#define _LINUX_TIMER_TYPES_H + +#include <linux/lockdep_types.h> +#include <linux/types.h> + +struct timer_list { + /* + * All fields that change during normal runtime grouped to the + * same cacheline + */ + struct hlist_node entry; + unsigned long expires; + void (*function)(struct timer_list *); + u32 flags; + +#ifdef CONFIG_LOCKDEP + struct lockdep_map lockdep_map; +#endif +}; + +#endif /* _LINUX_TIMER_TYPES_H */ diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h index adc80e29168e..62973f7d4610 100644 --- a/include/linux/timerqueue.h +++ b/include/linux/timerqueue.h @@ -3,18 +3,7 @@ #define _LINUX_TIMERQUEUE_H #include <linux/rbtree.h> -#include <linux/ktime.h> - - -struct timerqueue_node { - struct rb_node node; - ktime_t expires; -}; - -struct timerqueue_head { - struct rb_root_cached rb_root; -}; - +#include <linux/timerqueue_types.h> extern bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node); diff --git a/include/linux/timerqueue_types.h b/include/linux/timerqueue_types.h new file mode 100644 index 000000000000..dc298d0923e3 --- /dev/null +++ b/include/linux/timerqueue_types.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TIMERQUEUE_TYPES_H +#define _LINUX_TIMERQUEUE_TYPES_H + +#include <linux/rbtree_types.h> +#include <linux/types.h> + +struct timerqueue_node { + struct rb_node node; + ktime_t expires; +}; + +struct timerqueue_head { + struct rb_root_cached rb_root; +}; + +#endif /* _LINUX_TIMERQUEUE_TYPES_H */ diff --git a/include/linux/torture.h b/include/linux/torture.h index c98d0c83d117..1541454da03e 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -21,6 +21,7 @@ #include <linux/debugobjects.h> #include <linux/bug.h> #include <linux/compiler.h> +#include <linux/hrtimer.h> /* Definitions for a non-string torture-test module parameter. */ #define torture_param(type, name, init, msg) \ diff --git a/include/linux/types.h b/include/linux/types.h index 253168bb3fe1..2bc8766ba20c 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -120,6 +120,9 @@ typedef s64 int64_t; #define aligned_be64 __aligned_be64 #define aligned_le64 __aligned_le64 +/* Nanosecond scalar representation for kernel time values */ +typedef s64 ktime_t; + /** * The type used for indexing onto a disc or disc partition. * diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h index 415a7ca2b882..f85ec5613721 100644 --- a/include/linux/uidgid.h +++ b/include/linux/uidgid.h @@ -12,22 +12,13 @@ * to detect when we overlook these differences. * */ -#include <linux/types.h> +#include <linux/uidgid_types.h> #include <linux/highuid.h> struct user_namespace; extern struct user_namespace init_user_ns; struct uid_gid_map; -typedef struct { - uid_t val; -} kuid_t; - - -typedef struct { - gid_t val; -} kgid_t; - #define KUIDT_INIT(value) (kuid_t){ value } #define KGIDT_INIT(value) (kgid_t){ value } diff --git a/include/linux/uidgid_types.h b/include/linux/uidgid_types.h new file mode 100644 index 000000000000..b35ac4955a33 --- /dev/null +++ b/include/linux/uidgid_types.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UIDGID_TYPES_H +#define _LINUX_UIDGID_TYPES_H + +#include <linux/types.h> + +typedef struct { + uid_t val; +} kuid_t; + +typedef struct { + gid_t val; +} kgid_t; + +#endif /* _LINUX_UIDGID_TYPES_H */ diff --git a/include/linux/wait.h b/include/linux/wait.h index 3473b663176f..8aa3372f21a0 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -9,7 +9,6 @@ #include <linux/spinlock.h> #include <asm/current.h> -#include <uapi/linux/wait.h> typedef struct wait_queue_entry wait_queue_entry_t; diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index b0b9604b76b8..2cc0a9606175 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -14,12 +14,7 @@ #include <linux/atomic.h> #include <linux/cpumask.h> #include <linux/rcupdate.h> - -struct workqueue_struct; - -struct work_struct; -typedef void (*work_func_t)(struct work_struct *work); -void delayed_work_timer_fn(struct timer_list *t); +#include <linux/workqueue_types.h> /* * The first word is the work queue pointer and the flags rolled into @@ -95,15 +90,6 @@ enum { #define WORK_STRUCT_FLAG_MASK ((1ul << WORK_STRUCT_FLAG_BITS) - 1) #define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) -struct work_struct { - atomic_long_t data; - struct list_head entry; - work_func_t func; -#ifdef CONFIG_LOCKDEP - struct lockdep_map lockdep_map; -#endif -}; - #define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)) diff --git a/include/linux/workqueue_types.h b/include/linux/workqueue_types.h new file mode 100644 index 000000000000..4c38824f3ab4 --- /dev/null +++ b/include/linux/workqueue_types.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_WORKQUEUE_TYPES_H +#define _LINUX_WORKQUEUE_TYPES_H + +#include <linux/atomic.h> +#include <linux/lockdep_types.h> +#include <linux/timer_types.h> +#include <linux/types.h> + +struct workqueue_struct; + +struct work_struct; +typedef void (*work_func_t)(struct work_struct *work); +void delayed_work_timer_fn(struct timer_list *t); + +struct work_struct { + atomic_long_t data; + struct list_head entry; + work_func_t func; +#ifdef CONFIG_LOCKDEP + struct lockdep_map lockdep_map; +#endif +}; + +#endif /* _LINUX_WORKQUEUE_TYPES_H */ diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h index ac5d6a3031db..4fc22908bc09 100644 --- a/include/uapi/linux/resource.h +++ b/include/uapi/linux/resource.h @@ -2,7 +2,7 @@ #ifndef _UAPI_LINUX_RESOURCE_H #define _UAPI_LINUX_RESOURCE_H -#include <linux/time.h> +#include <linux/time_types.h> #include <linux/types.h> /* |