*/
#include "sched.h"
+/*
+ * For documentation purposes, here are some membarrier ordering
+ * scenarios to keep in mind:
+ *
+ * A) Userspace thread execution after IPI vs membarrier's memory
+ * barrier before sending the IPI
+ *
+ * Userspace variables:
+ *
+ * int x = 0, y = 0;
+ *
+ * The memory barrier at the start of membarrier() on CPU0 is necessary in
+ * order to enforce the guarantee that any writes occurring on CPU0 before
+ * the membarrier() is executed will be visible to any code executing on
+ * CPU1 after the IPI-induced memory barrier:
+ *
+ * CPU0 CPU1
+ *
+ * x = 1
+ * membarrier():
+ * a: smp_mb()
+ * b: send IPI IPI-induced mb
+ * c: smp_mb()
+ * r2 = y
+ * y = 1
+ * barrier()
+ * r1 = x
+ *
+ * BUG_ON(r1 == 0 && r2 == 0)
+ *
+ * The write to y and load from x by CPU1 are unordered by the hardware,
+ * so it's possible to have "r1 = x" reordered before "y = 1" at any
+ * point after (b). If the memory barrier at (a) is omitted, then "x = 1"
+ * can be reordered after (a) (although not after (c)), so we get r1 == 0
+ * and r2 == 0. This violates the guarantee that membarrier() is
+ * supposed by provide.
+ *
+ * The timing of the memory barrier at (a) has to ensure that it executes
+ * before the IPI-induced memory barrier on CPU1.
+ *
+ * B) Userspace thread execution before IPI vs membarrier's memory
+ * barrier after completing the IPI
+ *
+ * Userspace variables:
+ *
+ * int x = 0, y = 0;
+ *
+ * The memory barrier at the end of membarrier() on CPU0 is necessary in
+ * order to enforce the guarantee that any writes occurring on CPU1 before
+ * the membarrier() is executed will be visible to any code executing on
+ * CPU0 after the membarrier():
+ *
+ * CPU0 CPU1
+ *
+ * x = 1
+ * barrier()
+ * y = 1
+ * r2 = y
+ * membarrier():
+ * a: smp_mb()
+ * b: send IPI IPI-induced mb
+ * c: smp_mb()
+ * r1 = x
+ * BUG_ON(r1 == 0 && r2 == 1)
+ *
+ * The writes to x and y are unordered by the hardware, so it's possible to
+ * have "r2 = 1" even though the write to x doesn't execute until (b). If
+ * the memory barrier at (c) is omitted then "r1 = x" can be reordered
+ * before (b) (although not before (a)), so we get "r1 = 0". This violates
+ * the guarantee that membarrier() is supposed to provide.
+ *
+ * The timing of the memory barrier at (c) has to ensure that it executes
+ * after the IPI-induced memory barrier on CPU1.
+ *
+ * C) Scheduling userspace thread -> kthread -> userspace thread vs membarrier
+ *
+ * CPU0 CPU1
+ *
+ * membarrier():
+ * a: smp_mb()
+ * d: switch to kthread (includes mb)
+ * b: read rq->curr->mm == NULL
+ * e: switch to user (includes mb)
+ * c: smp_mb()
+ *
+ * Using the scenario from (A), we can show that (a) needs to be paired
+ * with (e). Using the scenario from (B), we can show that (c) needs to
+ * be paired with (d).
+ *
+ * D) exit_mm vs membarrier
+ *
+ * Two thread groups are created, A and B. Thread group B is created by
+ * issuing clone from group A with flag CLONE_VM set, but not CLONE_THREAD.
+ * Let's assume we have a single thread within each thread group (Thread A
+ * and Thread B). Thread A runs on CPU0, Thread B runs on CPU1.
+ *
+ * CPU0 CPU1
+ *
+ * membarrier():
+ * a: smp_mb()
+ * exit_mm():
+ * d: smp_mb()
+ * e: current->mm = NULL
+ * b: read rq->curr->mm == NULL
+ * c: smp_mb()
+ *
+ * Using scenario (B), we can show that (c) needs to be paired with (d).
+ *
+ * E) kthread_{use,unuse}_mm vs membarrier
+ *
+ * CPU0 CPU1
+ *
+ * membarrier():
+ * a: smp_mb()
+ * kthread_unuse_mm()
+ * d: smp_mb()
+ * e: current->mm = NULL
+ * b: read rq->curr->mm == NULL
+ * kthread_use_mm()
+ * f: current->mm = mm
+ * g: smp_mb()
+ * c: smp_mb()
+ *
+ * Using the scenario from (A), we can show that (a) needs to be paired
+ * with (g). Using the scenario from (B), we can show that (c) needs to
+ * be paired with (d).
+ */
+
/*
* Bitmask made from a "or" of all commands within enum membarrier_cmd,
* except MEMBARRIER_CMD_QUERY.
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);
}
this_cpu_write(runqueues.membarrier_state, 0);
}
+void membarrier_update_current_mm(struct mm_struct *next_mm)
+{
+ struct rq *rq = this_rq();
+ int membarrier_state = 0;
+
+ if (next_mm)
+ membarrier_state = atomic_read(&next_mm->membarrier_state);
+ if (READ_ONCE(rq->membarrier_state) == membarrier_state)
+ return;
+ WRITE_ONCE(rq->membarrier_state, membarrier_state);
+}
+
static int membarrier_global_expedited(void)
{
int cpu;
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.
+ * Skip the CPU if it runs a kernel thread which is not using
+ * a task mm.
*/
p = rcu_dereference(cpu_rq(cpu)->curr);
- if (p->flags & PF_KTHREAD)
+ if (!p->mm)
continue;
__cpumask_set_cpu(cpu, tmpmask);
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;
return -EPERM;
}
- if (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1)
+ if (flags != MEMBARRIER_FLAG_SYNC_CORE &&
+ (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1))
return 0;
/*
if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_id))
goto out;
- if (cpu_id == raw_smp_processor_id())
- goto out;
rcu_read_lock();
p = rcu_dereference(cpu_rq(cpu_id)->curr);
if (!p || p->mm != mm) {
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;
p = rcu_dereference(cpu_rq(cpu)->curr);
if (p && p->mm == mm)
__cpumask_set_cpu(cpu, tmpmask);
rcu_read_unlock();
}
- preempt_disable();
- if (cpu_id >= 0)
+ 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
- smp_call_function_many(tmpmask, ipi_func, NULL, 1);
- preempt_enable();
+ } 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)
projects / linux-2.6-microblaze.git / blobdiff