We're trying to get sched.h down to more or less just types only, not code - rseq can live in its own header. This helps us kill the dependency on preempt.h in sched.h. Signed-off-by: Kent Overstreet <kent.overstreet@xxxxxxxxx> --- arch/x86/kernel/signal.c | 1 + fs/exec.c | 1 + include/linux/resume_user_mode.h | 1 + include/linux/rseq.h | 131 +++++++++++++++++++++++++++++++ include/linux/sched.h | 125 +---------------------------- kernel/fork.c | 1 + kernel/sched/core.c | 1 + 7 files changed, 137 insertions(+), 124 deletions(-) create mode 100644 include/linux/rseq.h diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 65fe2094da59..31b6f5dddfc2 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -27,6 +27,7 @@ #include <linux/context_tracking.h> #include <linux/entry-common.h> #include <linux/syscalls.h> +#include <linux/rseq.h> #include <asm/processor.h> #include <asm/ucontext.h> diff --git a/fs/exec.c b/fs/exec.c index 4aa19b24f281..41773af7e3dc 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -66,6 +66,7 @@ #include <linux/coredump.h> #include <linux/time_namespace.h> #include <linux/user_events.h> +#include <linux/rseq.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> 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/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/sched.h b/include/linux/sched.h index ec739277c39b..d528057c99e4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -34,7 +34,7 @@ #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> -#include <linux/rseq.h> +#include <uapi/linux/rseq.h> #include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> @@ -2180,129 +2180,6 @@ 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/kernel/fork.c b/kernel/fork.c index 319e61297bfb..53816393995b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -100,6 +100,7 @@ #include <linux/stackprotector.h> #include <linux/user_events.h> #include <linux/iommu.h> +#include <linux/rseq.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a708d225c28e..d04cf3c47899 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -57,6 +57,7 @@ #include <linux/profile.h> #include <linux/psi.h> #include <linux/rcuwait_api.h> +#include <linux/rseq.h> #include <linux/sched/wake_q.h> #include <linux/scs.h> #include <linux/slab.h> -- 2.43.0