diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 1c4e40c5efaf..03a169087a18 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -7,6 +7,7 @@ #include #include #include +#include /* * Routines for handling mm_structs @@ -223,12 +224,26 @@ enum { MEMBARRIER_STATE_PRIVATE_EXPEDITED = (1U << 1), MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY = (1U << 2), MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3), + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4), + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5), +}; + +enum { + MEMBARRIER_FLAG_SYNC_CORE = (1U << 0), }; #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS #include #endif +static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) +{ + if (likely(!(atomic_read(&mm->membarrier_state) & + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE))) + return; + sync_core_before_usermode(); +} + static inline void membarrier_execve(struct task_struct *t) { atomic_set(&t->mm->membarrier_state, 0); @@ -244,6 +259,9 @@ static inline void membarrier_arch_switch_mm(struct mm_struct *prev, static inline void membarrier_execve(struct task_struct *t) { } +static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) +{ +} #endif #endif /* _LINUX_SCHED_MM_H */ diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h index d252506e1b5e..5891d7614c8c 100644 --- a/include/uapi/linux/membarrier.h +++ b/include/uapi/linux/membarrier.h @@ -73,7 +73,7 @@ * to and return from the system call * (non-running threads are de facto in such a * state). This only covers threads from the - * same processes as the caller thread. This + * same process as the caller thread. This * command returns 0 on success. The * "expedited" commands complete faster than * the non-expedited ones, they never block, @@ -86,6 +86,34 @@ * Register the process intent to use * MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always * returns 0. + * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE: + * In addition to provide memory ordering + * guarantees described in + * MEMBARRIER_CMD_PRIVATE_EXPEDITED, ensure + * the caller thread, upon return from system + * call, that all its running threads siblings + * have executed a core serializing + * instruction. (architectures are required to + * guarantee that non-running threads issue + * core serializing instructions before they + * resume user-space execution). This only + * covers threads from the same process as the + * caller thread. This command returns 0 on + * success. The "expedited" commands complete + * faster than the non-expedited ones, they + * never block, but have the downside of + * causing extra overhead. If this command is + * not implemented by an architecture, -EINVAL + * is returned. A process needs to register its + * intent to use the private expedited sync + * core command prior to using it, otherwise + * this command returns -EPERM. + * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE: + * Register the process intent to use + * MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE. + * If this command is not implemented by an + * architecture, -EINVAL is returned. + * Returns 0 on success. * @MEMBARRIER_CMD_SHARED: * Alias to MEMBARRIER_CMD_GLOBAL. Provided for * header backward compatibility. @@ -101,6 +129,8 @@ enum membarrier_cmd { MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED = (1 << 2), MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3), MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4), + MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE = (1 << 5), + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE = (1 << 6), /* Alias for header backward compatibility. */ MEMBARRIER_CMD_SHARED = MEMBARRIER_CMD_GLOBAL, diff --git a/init/Kconfig b/init/Kconfig index 535421facea8..e37f4b2a6445 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1415,6 +1415,9 @@ config USERFAULTFD config ARCH_HAS_MEMBARRIER_CALLBACKS bool +config ARCH_HAS_MEMBARRIER_SYNC_CORE + bool + config EMBEDDED bool "Embedded system" option allnoconfig_y diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 11bf4d48d2d3..ee420d78e674 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2704,13 +2704,21 @@ static struct rq *finish_task_switch(struct task_struct *prev) fire_sched_in_preempt_notifiers(current); /* - * When transitioning from a kernel thread to a userspace - * thread, mmdrop()'s implicit full barrier is required by the - * membarrier system call, because the current ->active_mm can - * become the current mm without going through switch_mm(). + * When switching through a kernel thread, the loop in + * membarrier_{private,global}_expedited() may have observed that + * kernel thread and not issued an IPI. It is therefore possible to + * schedule between user->kernel->user threads without passing though + * switch_mm(). Membarrier requires a barrier after storing to + * rq->curr, before returning to userspace, so provide them here: + * + * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly + * provided by mmdrop(), + * - a sync_core for SYNC_CORE. */ - if (mm) + if (mm) { + membarrier_mm_sync_core_before_usermode(mm); mmdrop(mm); + } if (unlikely(prev_state == TASK_DEAD)) { if (prev->sched_class->task_dead) prev->sched_class->task_dead(prev); diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index d2087d5f9837..5d0762633639 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -26,11 +26,20 @@ * Bitmask made from a "or" of all commands within enum membarrier_cmd, * except MEMBARRIER_CMD_QUERY. */ +#ifdef CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE +#define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \ + (MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE \ + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE) +#else +#define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK 0 +#endif + #define MEMBARRIER_CMD_BITMASK \ (MEMBARRIER_CMD_GLOBAL | MEMBARRIER_CMD_GLOBAL_EXPEDITED \ | MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED \ | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ - | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED) + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED \ + | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK) static void ipi_mb(void *info) { @@ -104,15 +113,23 @@ static int membarrier_global_expedited(void) return 0; } -static int membarrier_private_expedited(void) +static int membarrier_private_expedited(int flags) { int cpu; bool fallback = false; cpumask_var_t tmpmask; - if (!(atomic_read(¤t->mm->membarrier_state) - & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)) - return -EPERM; + if (flags & MEMBARRIER_FLAG_SYNC_CORE) { + if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE)) + return -EINVAL; + if (!(atomic_read(¤t->mm->membarrier_state) & + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY)) + return -EPERM; + } else { + if (!(atomic_read(¤t->mm->membarrier_state) & + MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)) + return -EPERM; + } if (num_online_cpus() == 1) return 0; @@ -205,20 +222,29 @@ static int membarrier_register_global_expedited(void) return 0; } -static int membarrier_register_private_expedited(void) +static int membarrier_register_private_expedited(int flags) { struct task_struct *p = current; struct mm_struct *mm = p->mm; + int state = MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY; + + if (flags & MEMBARRIER_FLAG_SYNC_CORE) { + if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE)) + return -EINVAL; + state = MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY; + } /* * We need to consider threads belonging to different thread * groups, which use the same mm. (CLONE_VM but not * CLONE_THREAD). */ - if (atomic_read(&mm->membarrier_state) - & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY) + if (atomic_read(&mm->membarrier_state) & state) return 0; atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED, &mm->membarrier_state); + if (flags & MEMBARRIER_FLAG_SYNC_CORE) + atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE, + &mm->membarrier_state); if (!(atomic_read(&mm->mm_users) == 1 && get_nr_threads(p) == 1)) { /* * Ensure all future scheduler executions will observe the @@ -226,8 +252,7 @@ static int membarrier_register_private_expedited(void) */ synchronize_sched(); } - atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY, - &mm->membarrier_state); + atomic_or(state, &mm->membarrier_state); return 0; } @@ -283,9 +308,13 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) case MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED: return membarrier_register_global_expedited(); case MEMBARRIER_CMD_PRIVATE_EXPEDITED: - return membarrier_private_expedited(); + return membarrier_private_expedited(0); case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: - return membarrier_register_private_expedited(); + return membarrier_register_private_expedited(0); + case MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE: + return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE); + case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE: + return membarrier_register_private_expedited(MEMBARRIER_FLAG_SYNC_CORE); default: return -EINVAL; }