From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/kernel/sched/membarrier.c | 405 +++++++++++++++++++++++++++++++++++++++++----------------
1 files changed, 289 insertions(+), 116 deletions(-)
diff --git a/kernel/kernel/sched/membarrier.c b/kernel/kernel/sched/membarrier.c
index dd27e63..cc7cd51 100644
--- a/kernel/kernel/sched/membarrier.c
+++ b/kernel/kernel/sched/membarrier.c
@@ -1,17 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (C) 2010-2017 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
*
* 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 "sched.h"
@@ -27,22 +18,93 @@
#define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK 0
#endif
+#ifdef CONFIG_RSEQ
+#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \
+ (MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ \
+ | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ)
+#else
+#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_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_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK)
+ | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \
+ | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
static void ipi_mb(void *info)
{
smp_mb(); /* IPIs should be serializing but paranoid. */
}
+static void ipi_sync_core(void *info)
+{
+ /*
+ * The smp_mb() in membarrier after all the IPIs is supposed to
+ * ensure that memory on remote CPUs that occur before the IPI
+ * become visible to membarrier()'s caller -- see scenario B in
+ * the big comment at the top of this file.
+ *
+ * A sync_core() would provide this guarantee, but
+ * sync_core_before_usermode() might end up being deferred until
+ * after membarrier()'s smp_mb().
+ */
+ smp_mb(); /* IPIs should be serializing but paranoid. */
+
+ sync_core_before_usermode();
+}
+
+static void ipi_rseq(void *info)
+{
+ /*
+ * Ensure that all stores done by the calling thread are visible
+ * to the current task before the current task resumes. We could
+ * probably optimize this away on most architectures, but by the
+ * time we've already sent an IPI, the cost of the extra smp_mb()
+ * is negligible.
+ */
+ smp_mb();
+ rseq_preempt(current);
+}
+
+static void ipi_sync_rq_state(void *info)
+{
+ struct mm_struct *mm = (struct mm_struct *) info;
+
+ if (current->mm != mm)
+ return;
+ this_cpu_write(runqueues.membarrier_state,
+ atomic_read(&mm->membarrier_state));
+ /*
+ * Issue a memory barrier after setting
+ * MEMBARRIER_STATE_GLOBAL_EXPEDITED in the current runqueue to
+ * guarantee that no memory access following registration is reordered
+ * before registration.
+ */
+ smp_mb();
+}
+
+void membarrier_exec_mmap(struct mm_struct *mm)
+{
+ /*
+ * Issue a memory barrier before clearing membarrier_state to
+ * guarantee that no memory access prior to exec is reordered after
+ * clearing this state.
+ */
+ smp_mb();
+ atomic_set(&mm->membarrier_state, 0);
+ /*
+ * Keep the runqueue membarrier_state in sync with this mm
+ * membarrier_state.
+ */
+ this_cpu_write(runqueues.membarrier_state, 0);
+}
+
static int membarrier_global_expedited(void)
{
int cpu;
- bool fallback = false;
cpumask_var_t tmpmask;
if (num_online_cpus() == 1)
@@ -54,17 +116,11 @@
*/
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;
- }
+ if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+ return -ENOMEM;
cpus_read_lock();
+ rcu_read_lock();
for_each_online_cpu(cpu) {
struct task_struct *p;
@@ -79,23 +135,28 @@
if (cpu == raw_smp_processor_id())
continue;
- rcu_read_lock();
- p = task_rcu_dereference(&cpu_rq(cpu)->curr);
- if (p && p->mm && (atomic_read(&p->mm->membarrier_state) &
- MEMBARRIER_STATE_GLOBAL_EXPEDITED)) {
- if (!fallback)
- __cpumask_set_cpu(cpu, tmpmask);
- else
- smp_call_function_single(cpu, ipi_mb, NULL, 1);
- }
- rcu_read_unlock();
+ if (!(READ_ONCE(cpu_rq(cpu)->membarrier_state) &
+ MEMBARRIER_STATE_GLOBAL_EXPEDITED))
+ continue;
+
+ /*
+ * Skip the CPU if it runs a kernel thread. The scheduler
+ * leaves the prior task mm in place as an optimization when
+ * scheduling a kthread.
+ */
+ p = rcu_dereference(cpu_rq(cpu)->curr);
+ if (p->flags & PF_KTHREAD)
+ continue;
+
+ __cpumask_set_cpu(cpu, tmpmask);
}
- if (!fallback) {
- preempt_disable();
- smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
- preempt_enable();
- free_cpumask_var(tmpmask);
- }
+ rcu_read_unlock();
+
+ preempt_disable();
+ smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+ preempt_enable();
+
+ free_cpumask_var(tmpmask);
cpus_read_unlock();
/*
@@ -107,25 +168,35 @@
return 0;
}
-static int membarrier_private_expedited(int flags)
+static int membarrier_private_expedited(int flags, int cpu_id)
{
- int cpu;
- bool fallback = false;
cpumask_var_t tmpmask;
+ struct mm_struct *mm = current->mm;
+ smp_call_func_t ipi_func = ipi_mb;
- if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+ if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
return -EINVAL;
- if (!(atomic_read(¤t->mm->membarrier_state) &
+ if (!(atomic_read(&mm->membarrier_state) &
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY))
return -EPERM;
+ ipi_func = ipi_sync_core;
+ } else if (flags == MEMBARRIER_FLAG_RSEQ) {
+ if (!IS_ENABLED(CONFIG_RSEQ))
+ return -EINVAL;
+ if (!(atomic_read(&mm->membarrier_state) &
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY))
+ return -EPERM;
+ ipi_func = ipi_rseq;
} else {
- if (!(atomic_read(¤t->mm->membarrier_state) &
+ WARN_ON_ONCE(flags);
+ if (!(atomic_read(&mm->membarrier_state) &
MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
return -EPERM;
}
- if (num_online_cpus() == 1)
+ if (flags != MEMBARRIER_FLAG_SYNC_CORE &&
+ (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1))
return 0;
/*
@@ -134,46 +205,73 @@
*/
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;
- }
+ if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+ return -ENOMEM;
cpus_read_lock();
- for_each_online_cpu(cpu) {
+
+ if (cpu_id >= 0) {
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;
+ if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_id))
+ goto out;
rcu_read_lock();
- p = task_rcu_dereference(&cpu_rq(cpu)->curr);
- if (p && p->mm == current->mm) {
- if (!fallback)
+ p = rcu_dereference(cpu_rq(cpu_id)->curr);
+ if (!p || p->mm != mm) {
+ rcu_read_unlock();
+ goto out;
+ }
+ rcu_read_unlock();
+ } else {
+ int cpu;
+
+ rcu_read_lock();
+ for_each_online_cpu(cpu) {
+ struct task_struct *p;
+
+ p = rcu_dereference(cpu_rq(cpu)->curr);
+ if (p && p->mm == mm)
__cpumask_set_cpu(cpu, tmpmask);
- else
- smp_call_function_single(cpu, ipi_mb, NULL, 1);
}
rcu_read_unlock();
}
- if (!fallback) {
- preempt_disable();
- smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
- preempt_enable();
- free_cpumask_var(tmpmask);
+
+ if (cpu_id >= 0) {
+ /*
+ * smp_call_function_single() will call ipi_func() if cpu_id
+ * is the calling CPU.
+ */
+ smp_call_function_single(cpu_id, ipi_func, NULL, 1);
+ } else {
+ /*
+ * For regular membarrier, we can save a few cycles by
+ * skipping the current cpu -- we're about to do smp_mb()
+ * below, and if we migrate to a different cpu, this cpu
+ * and the new cpu will execute a full barrier in the
+ * scheduler.
+ *
+ * For SYNC_CORE, we do need a barrier on the current cpu --
+ * otherwise, if we are migrated and replaced by a different
+ * task in the same mm just before, during, or after
+ * membarrier, we will end up with some thread in the mm
+ * running without a core sync.
+ *
+ * For RSEQ, don't rseq_preempt() the caller. User code
+ * is not supposed to issue syscalls at all from inside an
+ * rseq critical section.
+ */
+ if (flags != MEMBARRIER_FLAG_SYNC_CORE) {
+ preempt_disable();
+ smp_call_function_many(tmpmask, ipi_func, NULL, true);
+ preempt_enable();
+ } else {
+ on_each_cpu_mask(tmpmask, ipi_func, NULL, true);
+ }
}
+
+out:
+ if (cpu_id < 0)
+ free_cpumask_var(tmpmask);
cpus_read_unlock();
/*
@@ -182,6 +280,63 @@
* rq->curr modification in scheduler.
*/
smp_mb(); /* exit from system call is not a mb */
+
+ return 0;
+}
+
+static int sync_runqueues_membarrier_state(struct mm_struct *mm)
+{
+ int membarrier_state = atomic_read(&mm->membarrier_state);
+ cpumask_var_t tmpmask;
+ int cpu;
+
+ if (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1) {
+ this_cpu_write(runqueues.membarrier_state, membarrier_state);
+
+ /*
+ * For single mm user, we can simply issue a memory barrier
+ * after setting MEMBARRIER_STATE_GLOBAL_EXPEDITED in the
+ * mm and in the current runqueue to guarantee that no memory
+ * access following registration is reordered before
+ * registration.
+ */
+ smp_mb();
+ return 0;
+ }
+
+ if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+ return -ENOMEM;
+
+ /*
+ * For mm with multiple users, we need to ensure all future
+ * scheduler executions will observe @mm's new membarrier
+ * state.
+ */
+ synchronize_rcu();
+
+ /*
+ * For each cpu runqueue, if the task's mm match @mm, ensure that all
+ * @mm's membarrier state set bits are also set in the runqueue's
+ * membarrier state. This ensures that a runqueue scheduling
+ * between threads which are users of @mm has its membarrier state
+ * updated.
+ */
+ cpus_read_lock();
+ rcu_read_lock();
+ for_each_online_cpu(cpu) {
+ struct rq *rq = cpu_rq(cpu);
+ struct task_struct *p;
+
+ p = rcu_dereference(rq->curr);
+ if (p && p->mm == mm)
+ __cpumask_set_cpu(cpu, tmpmask);
+ }
+ rcu_read_unlock();
+
+ on_each_cpu_mask(tmpmask, ipi_sync_rq_state, mm, true);
+
+ free_cpumask_var(tmpmask);
+ cpus_read_unlock();
return 0;
}
@@ -190,28 +345,15 @@
{
struct task_struct *p = current;
struct mm_struct *mm = p->mm;
+ int ret;
if (atomic_read(&mm->membarrier_state) &
MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY)
return 0;
atomic_or(MEMBARRIER_STATE_GLOBAL_EXPEDITED, &mm->membarrier_state);
- if (atomic_read(&mm->mm_users) == 1 && get_nr_threads(p) == 1) {
- /*
- * For single mm user, single threaded process, we can
- * simply issue a memory barrier after setting
- * MEMBARRIER_STATE_GLOBAL_EXPEDITED to guarantee that
- * no memory access following registration is reordered
- * before registration.
- */
- smp_mb();
- } else {
- /*
- * For multi-mm user threads, we need to ensure all
- * future scheduler executions will observe the new
- * thread flag state for this mm.
- */
- synchronize_sched();
- }
+ ret = sync_runqueues_membarrier_state(mm);
+ if (ret)
+ return ret;
atomic_or(MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY,
&mm->membarrier_state);
@@ -222,12 +364,22 @@
{
struct task_struct *p = current;
struct mm_struct *mm = p->mm;
- int state = MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY;
+ int ready_state = MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY,
+ set_state = MEMBARRIER_STATE_PRIVATE_EXPEDITED,
+ ret;
- if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+ 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;
+ ready_state =
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY;
+ } else if (flags == MEMBARRIER_FLAG_RSEQ) {
+ if (!IS_ENABLED(CONFIG_RSEQ))
+ return -EINVAL;
+ ready_state =
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY;
+ } else {
+ WARN_ON_ONCE(flags);
}
/*
@@ -235,35 +387,41 @@
* groups, which use the same mm. (CLONE_VM but not
* CLONE_THREAD).
*/
- if ((atomic_read(&mm->membarrier_state) & state) == state)
+ if ((atomic_read(&mm->membarrier_state) & ready_state) == ready_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
- * new thread flag state for this process.
- */
- synchronize_sched();
- }
- atomic_or(state, &mm->membarrier_state);
+ set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE;
+ if (flags & MEMBARRIER_FLAG_RSEQ)
+ set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ;
+ atomic_or(set_state, &mm->membarrier_state);
+ ret = sync_runqueues_membarrier_state(mm);
+ if (ret)
+ return ret;
+ atomic_or(ready_state, &mm->membarrier_state);
return 0;
}
/**
* 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.
+ * @cmd: Takes command values defined in enum membarrier_cmd.
+ * @flags: Currently needs to be 0 for all commands other than
+ * MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ: in the latter
+ * case it can be MEMBARRIER_CMD_FLAG_CPU, indicating that @cpu_id
+ * contains the CPU on which to interrupt (= restart)
+ * the RSEQ critical section.
+ * @cpu_id: if @flags == MEMBARRIER_CMD_FLAG_CPU, indicates the cpu on which
+ * RSEQ CS should be interrupted (@cmd must be
+ * MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ).
*
* 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.
+ * if this system call returns -ENOSYS or -EINVAL, it is guaranteed to
+ * always return the same value until reboot. In addition, it can return
+ * -ENOMEM if there is not enough memory available to perform the system
+ * call.
*
* All memory accesses performed in program order from each targeted thread
* is guaranteed to be ordered with respect to sys_membarrier(). If we use
@@ -280,10 +438,21 @@
* smp_mb() X O O
* sys_membarrier() O O O
*/
-SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
+SYSCALL_DEFINE3(membarrier, int, cmd, unsigned int, flags, int, cpu_id)
{
- if (unlikely(flags))
- return -EINVAL;
+ switch (cmd) {
+ case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+ if (unlikely(flags && flags != MEMBARRIER_CMD_FLAG_CPU))
+ return -EINVAL;
+ break;
+ default:
+ if (unlikely(flags))
+ return -EINVAL;
+ }
+
+ if (!(flags & MEMBARRIER_CMD_FLAG_CPU))
+ cpu_id = -1;
+
switch (cmd) {
case MEMBARRIER_CMD_QUERY:
{
@@ -298,20 +467,24 @@
if (tick_nohz_full_enabled())
return -EINVAL;
if (num_online_cpus() > 1)
- synchronize_sched();
+ synchronize_rcu();
return 0;
case MEMBARRIER_CMD_GLOBAL_EXPEDITED:
return membarrier_global_expedited();
case MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED:
return membarrier_register_global_expedited();
case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
- return membarrier_private_expedited(0);
+ return membarrier_private_expedited(0, cpu_id);
case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
return membarrier_register_private_expedited(0);
case MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE:
- return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+ return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE, cpu_id);
case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE:
return membarrier_register_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+ case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+ return membarrier_private_expedited(MEMBARRIER_FLAG_RSEQ, cpu_id);
+ case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+ return membarrier_register_private_expedited(MEMBARRIER_FLAG_RSEQ);
default:
return -EINVAL;
}
--
Gitblit v1.6.2