From 3ccfebedd8cf54e291c809c838d8ad5cc00f5688 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Mon, 29 Jan 2018 15:20:11 -0500 Subject: [PATCH] powerpc, membarrier: Skip memory barrier in switch_mm() Allow PowerPC to skip the full memory barrier in switch_mm(), and only issue the barrier when scheduling into a task belonging to a process that has registered to use expedited private. Threads targeting the same VM but which belong to different thread groups is a tricky case. It has a few consequences: It turns out that we cannot rely on get_nr_threads(p) to count the number of threads using a VM. We can use (atomic_read(&mm->mm_users) == 1 && get_nr_threads(p) == 1) instead to skip the synchronize_sched() for cases where the VM only has a single user, and that user only has a single thread. It also turns out that we cannot use for_each_thread() to set thread flags in all threads using a VM, as it only iterates on the thread group. Therefore, test the membarrier state variable directly rather than relying on thread flags. This means membarrier_register_private_expedited() needs to set the MEMBARRIER_STATE_PRIVATE_EXPEDITED flag, issue synchronize_sched(), and only then set MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY which allows private expedited membarrier commands to succeed. membarrier_arch_switch_mm() now tests for the MEMBARRIER_STATE_PRIVATE_EXPEDITED flag. Signed-off-by: Mathieu Desnoyers Acked-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Alan Stern Cc: Alexander Viro 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: Linus Torvalds Cc: Maged Michael Cc: Michael Ellerman Cc: Nicholas Piggin 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 Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20180129202020.8515-3-mathieu.desnoyers@efficios.com Signed-off-by: Ingo Molnar --- MAINTAINERS | 1 + arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/membarrier.h | 26 ++++++++++++++++++++++++++ arch/powerpc/mm/mmu_context.c | 7 +++++++ include/linux/sched/mm.h | 13 ++++++++++++- init/Kconfig | 3 +++ kernel/sched/core.c | 10 ---------- kernel/sched/membarrier.c | 8 ++++++++ 8 files changed, 58 insertions(+), 11 deletions(-) create mode 100644 arch/powerpc/include/asm/membarrier.h diff --git a/MAINTAINERS b/MAINTAINERS index 217a8759e897..8e96d4e9677b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8944,6 +8944,7 @@ L: linux-kernel@vger.kernel.org S: Supported F: kernel/sched/membarrier.c F: include/uapi/linux/membarrier.h +F: arch/powerpc/include/asm/membarrier.h MEMORY MANAGEMENT L: linux-mm@kvack.org diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2ed525a44734..a2380de50878 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -140,6 +140,7 @@ config PPC select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_PMEM_API if PPC64 + select ARCH_HAS_MEMBARRIER_CALLBACKS select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE select ARCH_HAS_SG_CHAIN select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST diff --git a/arch/powerpc/include/asm/membarrier.h b/arch/powerpc/include/asm/membarrier.h new file mode 100644 index 000000000000..98ff4f1fcf2b --- /dev/null +++ b/arch/powerpc/include/asm/membarrier.h @@ -0,0 +1,26 @@ +#ifndef _ASM_POWERPC_MEMBARRIER_H +#define _ASM_POWERPC_MEMBARRIER_H + +static inline void membarrier_arch_switch_mm(struct mm_struct *prev, + struct mm_struct *next, + struct task_struct *tsk) +{ + /* + * Only need the full barrier when switching between processes. + * Barrier when switching from kernel to userspace is not + * required here, given that it is implied by mmdrop(). Barrier + * when switching from userspace to kernel is not needed after + * store to rq->curr. + */ + if (likely(!(atomic_read(&next->membarrier_state) & + MEMBARRIER_STATE_PRIVATE_EXPEDITED) || !prev)) + return; + + /* + * The membarrier system call requires a full memory barrier + * after storing to rq->curr, before going back to user-space. + */ + smp_mb(); +} + +#endif /* _ASM_POWERPC_MEMBARRIER_H */ diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c index d60a62bf4fc7..0ab297c4cfad 100644 --- a/arch/powerpc/mm/mmu_context.c +++ b/arch/powerpc/mm/mmu_context.c @@ -12,6 +12,7 @@ #include #include +#include #include @@ -58,6 +59,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * * On the read side the barrier is in pte_xchg(), which orders * the store to the PTE vs the load of mm_cpumask. + * + * This full barrier is needed by membarrier when switching + * between processes after store to rq->curr, before user-space + * memory accesses. */ smp_mb(); @@ -80,6 +85,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, if (new_on_cpu) radix_kvm_prefetch_workaround(next); + else + membarrier_arch_switch_mm(prev, next, tsk); /* * The actual HW switching method differs between the various diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 3d49b91b674d..26307cdc3969 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -215,14 +215,25 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) #ifdef CONFIG_MEMBARRIER enum { MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), - MEMBARRIER_STATE_SWITCH_MM = (1U << 1), + MEMBARRIER_STATE_PRIVATE_EXPEDITED = (1U << 1), }; +#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS +#include +#endif + static inline void membarrier_execve(struct task_struct *t) { atomic_set(&t->mm->membarrier_state, 0); } #else +#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS +static inline void membarrier_arch_switch_mm(struct mm_struct *prev, + struct mm_struct *next, + struct task_struct *tsk) +{ +} +#endif static inline void membarrier_execve(struct task_struct *t) { } diff --git a/init/Kconfig b/init/Kconfig index a9a2e2c86671..837adcf075d9 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1412,6 +1412,9 @@ config USERFAULTFD Enable the userfaultfd() system call that allows to intercept and handle page faults in userland. +config ARCH_HAS_MEMBARRIER_CALLBACKS + bool + config EMBEDDED bool "Embedded system" option allnoconfig_y diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3da7a2444a91..ead0c2135d47 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2698,16 +2698,6 @@ static struct rq *finish_task_switch(struct task_struct *prev) prev_state = prev->state; vtime_task_switch(prev); perf_event_task_sched_in(prev, current); - /* - * The membarrier system call requires a full memory barrier - * after storing to rq->curr, before going back to user-space. - * - * TODO: This smp_mb__after_unlock_lock can go away if PPC end - * up adding a full barrier to switch_mm(), or we should figure - * out if a smp_mb__after_unlock_lock is really the proper API - * to use. - */ - smp_mb__after_unlock_lock(); finish_task(prev); finish_lock_switch(rq); finish_arch_post_lock_switch(); diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 9bcbacba82a8..678577267a9a 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -118,6 +118,14 @@ static void membarrier_register_private_expedited(void) if (atomic_read(&mm->membarrier_state) & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY) return; + atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED, &mm->membarrier_state); + if (!(atomic_read(&mm->mm_users) == 1 && get_nr_threads(p) == 1)) { + /* + * Ensure all future scheduler executions will observe the + * new thread flag state for this process. + */ + synchronize_sched(); + } atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY, &mm->membarrier_state); }