From c5f58bd58f432be5d92df33c5458e0bcbee3aadf Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Mon, 29 Jan 2018 15:20:13 -0500 Subject: membarrier: Provide GLOBAL_EXPEDITED command Allow expedited membarrier to be used for data shared between processes through shared memory. Processes wishing to receive the membarriers register with MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED. Those which want to issue membarrier invoke MEMBARRIER_CMD_GLOBAL_EXPEDITED. This allows extremely simple kernel-level implementation: we have almost everything we need with the PRIVATE_EXPEDITED barrier code. All we need to do is to add a flag in the mm_struct that will be used to check whether we need to send the IPI to the current thread of each CPU. There is a slight downside to this approach compared to targeting specific shared memory users: when performing a membarrier operation, all registered "global" receivers will get the barrier, even if they don't share a memory mapping with the sender issuing MEMBARRIER_CMD_GLOBAL_EXPEDITED. This registration approach seems to fit the requirement of not disturbing processes that really deeply care about real-time: they simply should not register with MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED. In order to align the membarrier command names, the "MEMBARRIER_CMD_SHARED" command is renamed to "MEMBARRIER_CMD_GLOBAL", keeping an alias of MEMBARRIER_CMD_SHARED to MEMBARRIER_CMD_GLOBAL for UAPI header backward compatibility. Signed-off-by: Mathieu Desnoyers Acked-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Andrea Parri Cc: Andrew Hunter Cc: Andy Lutomirski Cc: Avi Kivity Cc: Benjamin Herrenschmidt Cc: Boqun Feng Cc: Dave Watson Cc: David Sehr Cc: Greg Hackmann Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Maged Michael Cc: Michael Ellerman Cc: Paul E. McKenney Cc: Paul Mackerras Cc: Russell King Cc: Will Deacon Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/20180129202020.8515-5-mathieu.desnoyers@efficios.com Signed-off-by: Ingo Molnar --- include/uapi/linux/membarrier.h | 42 ++++++++++++++++++++++++++++++++++------- 1 file changed, 35 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h index 4e01ad7ffe98..d252506e1b5e 100644 --- a/include/uapi/linux/membarrier.h +++ b/include/uapi/linux/membarrier.h @@ -31,7 +31,7 @@ * enum membarrier_cmd - membarrier system call command * @MEMBARRIER_CMD_QUERY: Query the set of supported commands. It returns * a bitmask of valid commands. - * @MEMBARRIER_CMD_SHARED: Execute a memory barrier on all running threads. + * @MEMBARRIER_CMD_GLOBAL: Execute a memory barrier on all running threads. * Upon return from system call, the caller thread * is ensured that all running threads have passed * through a state where all memory accesses to @@ -40,6 +40,28 @@ * (non-running threads are de facto in such a * state). This covers threads from all processes * running on the system. This command returns 0. + * @MEMBARRIER_CMD_GLOBAL_EXPEDITED: + * Execute a memory barrier on all running threads + * of all processes which previously registered + * with MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED. + * Upon return from system call, the caller thread + * is ensured that all running threads have passed + * through a state where all memory accesses to + * user-space addresses match program order between + * entry to and return from the system call + * (non-running threads are de facto in such a + * state). This only covers threads from processes + * which registered with + * MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED. + * This command returns 0. Given that + * registration is about the intent to receive + * the barriers, it is valid to invoke + * MEMBARRIER_CMD_GLOBAL_EXPEDITED from a + * non-registered process. + * @MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED: + * Register the process intent to receive + * MEMBARRIER_CMD_GLOBAL_EXPEDITED memory + * barriers. Always returns 0. * @MEMBARRIER_CMD_PRIVATE_EXPEDITED: * Execute a memory barrier on each running * thread belonging to the same process as the current @@ -64,18 +86,24 @@ * Register the process intent to use * MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always * returns 0. + * @MEMBARRIER_CMD_SHARED: + * Alias to MEMBARRIER_CMD_GLOBAL. Provided for + * header backward compatibility. * * Command to be passed to the membarrier system call. The commands need to * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to * the value 0. */ enum membarrier_cmd { - MEMBARRIER_CMD_QUERY = 0, - MEMBARRIER_CMD_SHARED = (1 << 0), - /* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */ - /* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */ - MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3), - MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4), + MEMBARRIER_CMD_QUERY = 0, + MEMBARRIER_CMD_GLOBAL = (1 << 0), + MEMBARRIER_CMD_GLOBAL_EXPEDITED = (1 << 1), + MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED = (1 << 2), + MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3), + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4), + + /* Alias for header backward compatibility. */ + MEMBARRIER_CMD_SHARED = MEMBARRIER_CMD_GLOBAL, }; #endif /* _UAPI_LINUX_MEMBARRIER_H */ -- cgit v1.2.3 From 70216e18e519a54a2f13569e8caff99a092a92d6 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Mon, 29 Jan 2018 15:20:17 -0500 Subject: membarrier: Provide core serializing command, *_SYNC_CORE Provide core serializing membarrier command to support memory reclaim by JIT. Each architecture needs to explicitly opt into that support by documenting in their architecture code how they provide the core serializing instructions required when returning from the membarrier IPI, and after the scheduler has updated the curr->mm pointer (before going back to user-space). They should then select ARCH_HAS_MEMBARRIER_SYNC_CORE to enable support for that command on their architecture. Architectures selecting this feature need to either document that they issue core serializing instructions when returning to user-space, or implement their architecture-specific sync_core_before_usermode(). Signed-off-by: Mathieu Desnoyers Acked-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Andrea Parri Cc: Andrew Hunter Cc: Andy Lutomirski Cc: Avi Kivity Cc: Benjamin Herrenschmidt Cc: Boqun Feng Cc: Dave Watson Cc: David Sehr Cc: Greg Hackmann Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Maged Michael Cc: Michael Ellerman Cc: Paul E. McKenney Cc: Paul Mackerras Cc: Russell King Cc: Will Deacon Cc: linux-api@vger.kernel.org Cc: linux-arch@vger.kernel.org Link: http://lkml.kernel.org/r/20180129202020.8515-9-mathieu.desnoyers@efficios.com Signed-off-by: Ingo Molnar --- include/linux/sched/mm.h | 18 ++++++++++++++ include/uapi/linux/membarrier.h | 32 ++++++++++++++++++++++++- init/Kconfig | 3 +++ kernel/sched/core.c | 18 ++++++++++---- kernel/sched/membarrier.c | 53 +++++++++++++++++++++++++++++++---------- 5 files changed, 106 insertions(+), 18 deletions(-) (limited to 'include/uapi') 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; } -- cgit v1.2.3