From 22e4ebb975822833b083533035233d128b30e98f Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 28 Jul 2017 16:40:40 -0400 Subject: membarrier: Provide expedited private command Implement MEMBARRIER_CMD_PRIVATE_EXPEDITED with IPIs using cpumask built from all runqueues for which current thread's mm is the same as the thread calling sys_membarrier. It executes faster than the non-expedited variant (no blocking). It also works on NOHZ_FULL configurations. Scheduler-wise, it requires a memory barrier before and after context switching between processes (which have different mm). The memory barrier before context switch is already present. For the barrier after context switch: * Our TSO archs can do RELEASE without being a full barrier. Look at x86 spin_unlock() being a regular STORE for example. But for those archs, all atomics imply smp_mb and all of them have atomic ops in switch_mm() for mm_cpumask(), and on x86 the CR3 load acts as a full barrier. * From all weakly ordered machines, only ARM64 and PPC can do RELEASE, the rest does indeed do smp_mb(), so there the spin_unlock() is a full barrier and we're good. * ARM64 has a very heavy barrier in switch_to(), which suffices. * PPC just removed its barrier from switch_to(), but appears to be talking about adding something to switch_mm(). So add a smp_mb__after_unlock_lock() for now, until this is settled on the PPC side. Changes since v3: - Properly document the memory barriers provided by each architecture. Changes since v2: - Address comments from Peter Zijlstra, - Add smp_mb__after_unlock_lock() after finish_lock_switch() in finish_task_switch() to add the memory barrier we need after storing to rq->curr. This is much simpler than the previous approach relying on atomic_dec_and_test() in mmdrop(), which actually added a memory barrier in the common case of switching between userspace processes. - Return -EINVAL when MEMBARRIER_CMD_SHARED is used on a nohz_full kernel, rather than having the whole membarrier system call returning -ENOSYS. Indeed, CMD_PRIVATE_EXPEDITED is compatible with nohz_full. Adapt the CMD_QUERY mask accordingly. Changes since v1: - move membarrier code under kernel/sched/ because it uses the scheduler runqueue, - only add the barrier when we switch from a kernel thread. The case where we switch from a user-space thread is already handled by the atomic_dec_and_test() in mmdrop(). - add a comment to mmdrop() documenting the requirement on the implicit memory barrier. CC: Peter Zijlstra CC: Paul E. McKenney CC: Boqun Feng CC: Andrew Hunter CC: Maged Michael CC: gromer@google.com CC: Avi Kivity CC: Benjamin Herrenschmidt CC: Paul Mackerras CC: Michael Ellerman Signed-off-by: Mathieu Desnoyers Signed-off-by: Paul E. McKenney Tested-by: Dave Watson --- kernel/sched/Makefile | 1 + kernel/sched/core.c | 25 ++++++++ kernel/sched/membarrier.c | 152 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 178 insertions(+) create mode 100644 kernel/sched/membarrier.c (limited to 'kernel/sched') diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 53f0164ed362..78f54932ea1d 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -25,3 +25,4 @@ obj-$(CONFIG_SCHED_DEBUG) += debug.o obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o +obj-$(CONFIG_MEMBARRIER) += membarrier.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bfee6ea7db49..f77269c6c2f8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2640,6 +2640,16 @@ 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_lock_switch(rq, prev); finish_arch_post_lock_switch(); @@ -3329,6 +3339,21 @@ static void __sched notrace __schedule(bool preempt) if (likely(prev != next)) { rq->nr_switches++; rq->curr = next; + /* + * The membarrier system call requires each architecture + * to have a full memory barrier after updating + * rq->curr, before returning to user-space. For TSO + * (e.g. x86), the architecture must provide its own + * barrier in switch_mm(). For weakly ordered machines + * for which spin_unlock() acts as a full memory + * barrier, finish_lock_switch() in common code takes + * care of this barrier. For weakly ordered machines for + * which spin_unlock() acts as a RELEASE barrier (only + * arm64 and PowerPC), arm64 has a full barrier in + * switch_to(), and PowerPC has + * smp_mb__after_unlock_lock() before + * finish_lock_switch(). + */ ++*switch_count; trace_sched_switch(preempt, prev, next); diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c new file mode 100644 index 000000000000..a92fddc22747 --- /dev/null +++ b/kernel/sched/membarrier.c @@ -0,0 +1,152 @@ +/* + * Copyright (C) 2010-2017 Mathieu Desnoyers + * + * membarrier system call + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include + +#include "sched.h" /* for cpu_rq(). */ + +/* + * Bitmask made from a "or" of all commands within enum membarrier_cmd, + * except MEMBARRIER_CMD_QUERY. + */ +#define MEMBARRIER_CMD_BITMASK \ + (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED) + +static void ipi_mb(void *info) +{ + smp_mb(); /* IPIs should be serializing but paranoid. */ +} + +static void membarrier_private_expedited(void) +{ + int cpu; + bool fallback = false; + cpumask_var_t tmpmask; + + if (num_online_cpus() == 1) + return; + + /* + * Matches memory barriers around rq->curr modification in + * scheduler. + */ + smp_mb(); /* system call entry is not a mb. */ + + /* + * Expedited membarrier commands guarantee that they won't + * block, hence the GFP_NOWAIT allocation flag and fallback + * implementation. + */ + if (!zalloc_cpumask_var(&tmpmask, GFP_NOWAIT)) { + /* Fallback for OOM. */ + fallback = true; + } + + cpus_read_lock(); + for_each_online_cpu(cpu) { + struct task_struct *p; + + /* + * Skipping the current CPU is OK even through we can be + * migrated at any point. The current CPU, at the point + * where we read raw_smp_processor_id(), is ensured to + * be in program order with respect to the caller + * thread. Therefore, we can skip this CPU from the + * iteration. + */ + if (cpu == raw_smp_processor_id()) + continue; + rcu_read_lock(); + p = task_rcu_dereference(&cpu_rq(cpu)->curr); + if (p && p->mm == current->mm) { + if (!fallback) + __cpumask_set_cpu(cpu, tmpmask); + else + smp_call_function_single(cpu, ipi_mb, NULL, 1); + } + rcu_read_unlock(); + } + if (!fallback) { + smp_call_function_many(tmpmask, ipi_mb, NULL, 1); + free_cpumask_var(tmpmask); + } + cpus_read_unlock(); + + /* + * Memory barrier on the caller thread _after_ we finished + * waiting for the last IPI. Matches memory barriers around + * rq->curr modification in scheduler. + */ + smp_mb(); /* exit from system call is not a mb */ +} + +/** + * sys_membarrier - issue memory barriers on a set of threads + * @cmd: Takes command values defined in enum membarrier_cmd. + * @flags: Currently needs to be 0. For future extensions. + * + * If this system call is not implemented, -ENOSYS is returned. If the + * command specified does not exist, not available on the running + * kernel, or if the command argument is invalid, this system call + * returns -EINVAL. For a given command, with flags argument set to 0, + * this system call is guaranteed to always return the same value until + * reboot. + * + * All memory accesses performed in program order from each targeted thread + * is guaranteed to be ordered with respect to sys_membarrier(). If we use + * the semantic "barrier()" to represent a compiler barrier forcing memory + * accesses to be performed in program order across the barrier, and + * smp_mb() to represent explicit memory barriers forcing full memory + * ordering across the barrier, we have the following ordering table for + * each pair of barrier(), sys_membarrier() and smp_mb(): + * + * The pair ordering is detailed as (O: ordered, X: not ordered): + * + * barrier() smp_mb() sys_membarrier() + * barrier() X X O + * smp_mb() X O O + * sys_membarrier() O O O + */ +SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) +{ + if (unlikely(flags)) + return -EINVAL; + switch (cmd) { + case MEMBARRIER_CMD_QUERY: + { + int cmd_mask = MEMBARRIER_CMD_BITMASK; + + if (tick_nohz_full_enabled()) + cmd_mask &= ~MEMBARRIER_CMD_SHARED; + return cmd_mask; + } + case MEMBARRIER_CMD_SHARED: + /* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */ + if (tick_nohz_full_enabled()) + return -EINVAL; + if (num_online_cpus() > 1) + synchronize_sched(); + return 0; + case MEMBARRIER_CMD_PRIVATE_EXPEDITED: + membarrier_private_expedited(); + return 0; + default: + return -EINVAL; + } +} -- cgit v1.2.3