This patchset is based on Google-internal RSEQ
work done by Paul Turner and Andrew Hunter.
When working with per-CPU RSEQ-based memory allocations,
it is sometimes important to make sure that a global
memory location is no longer accessed from RSEQ critical
sections. For example, there can be two per-CPU lists,
one is "active" and accessed per-CPU, while another one
is inactive and worked on asynchronously "off CPU" (e.g.
garbage collection is performed). Then at some point
the two lists are swapped, and a fast RCU-like mechanism
is required to make sure that the previously active
list is no longer accessed.
This patch introduces such a mechanism: in short,
membarrier() syscall issues an IPI to a CPU, restarting
a potentially active RSEQ critical section on the CPU.
v1->v2:
- removed the ability to IPI all CPUs in a single sycall;
- use task->mm rather than task->group_leader to identify
tasks belonging to the same process.
v2->v3:
- re-added the ability to IPI all CPUs in a single syscall;
- integrated with membarrier_private_expedited() to
make sure only CPUs running tasks with the same mm as
the current task are interrupted;
- also added MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ;
- flags in membarrier_private_expedited are never actually
bit flags but always distinct values (i.e. never two flags
are combined), so I modified bit testing to full equation
comparison for simplicity (otherwise the code needs to
work when several bits are set, for example).
The second patch in the patchset adds a selftest
of this feature.
Signed-off-by: Peter Oskolkov <[email protected]>
---
include/linux/sched/mm.h | 3 ++
include/uapi/linux/membarrier.h | 24 ++++++++++++++
kernel/sched/membarrier.c | 55 ++++++++++++++++++++++++++++-----
3 files changed, 74 insertions(+), 8 deletions(-)
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 6be66f52a2ad..477d5526e053 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -352,10 +352,13 @@ enum {
MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3),
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4),
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5),
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY = (1U << 6),
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ = (1U << 7),
};
enum {
MEMBARRIER_FLAG_SYNC_CORE = (1U << 0),
+ MEMBARRIER_FLAG_RSEQ = (1U << 1),
};
#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h
index 5891d7614c8c..f6bafe0676ba 100644
--- a/include/uapi/linux/membarrier.h
+++ b/include/uapi/linux/membarrier.h
@@ -114,6 +114,28 @@
* If this command is not implemented by an
* architecture, -EINVAL is returned.
* Returns 0 on success.
+ * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+ * In addition to provide memory ordering
+ * guarantees described in
+ * MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE,
+ * ensure the caller thread, upon return from
+ * system call, that all its running thread
+ * siblings have any currently running rseq
+ * critical sections restarted if @flags
+ * parameter is -1; if @flags parameter is >= 0,
+ * then this operation is performed only
+ * on CPU indicated by @flags. If this command is
+ * not implemented by an architecture, -EINVAL
+ * is returned. A process needs to register its
+ * intent to use the private expedited rseq
+ * command prior to using it, otherwise
+ * this command returns -EPERM.
+ * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+ * Register the process intent to use
+ * MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ.
+ * 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.
@@ -131,6 +153,8 @@ enum membarrier_cmd {
MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4),
MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE = (1 << 5),
MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE = (1 << 6),
+ MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ = (1 << 7),
+ MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ = (1 << 8),
/* Alias for header backward compatibility. */
MEMBARRIER_CMD_SHARED = MEMBARRIER_CMD_GLOBAL,
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 168479a7d61b..54c1093ebc87 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -18,6 +18,14 @@
#define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK 0
#endif
+#ifdef CONFIG_RSEQ
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK \
+ (MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ \
+ | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
+#else
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK 0
+#endif
+
#define MEMBARRIER_CMD_BITMASK \
(MEMBARRIER_CMD_GLOBAL | MEMBARRIER_CMD_GLOBAL_EXPEDITED \
| MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED \
@@ -27,6 +35,12 @@
static void ipi_mb(void *info)
{
+ int *flags = info;
+
+#ifdef CONFIG_RSEQ
+ if (flags && (*flags == MEMBARRIER_FLAG_RSEQ))
+ rseq_preempt(current);
+#endif
smp_mb(); /* IPIs should be serializing but paranoid. */
}
@@ -129,19 +143,26 @@ static int membarrier_global_expedited(void)
return 0;
}
-static int membarrier_private_expedited(int flags)
+static int membarrier_private_expedited(int flags, int cpu_id)
{
int cpu;
cpumask_var_t tmpmask;
struct mm_struct *mm = current->mm;
- 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(&mm->membarrier_state) &
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY))
return -EPERM;
+ } 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;
} else {
+ BUG_ON(flags != 0);
if (!(atomic_read(&mm->membarrier_state) &
MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
return -EPERM;
@@ -174,6 +195,8 @@ static int membarrier_private_expedited(int flags)
*/
if (cpu == raw_smp_processor_id())
continue;
+ if (cpu_id >= 0 && cpu != cpu_id)
+ continue;
p = rcu_dereference(cpu_rq(cpu)->curr);
if (p && p->mm == mm)
__cpumask_set_cpu(cpu, tmpmask);
@@ -181,7 +204,7 @@ static int membarrier_private_expedited(int flags)
rcu_read_unlock();
preempt_disable();
- smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+ smp_call_function_many(tmpmask, ipi_mb, &flags, 1);
preempt_enable();
free_cpumask_var(tmpmask);
@@ -283,11 +306,18 @@ static int membarrier_register_private_expedited(int
flags)
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;
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 {
+ BUG_ON(flags != 0);
}
/*
@@ -299,6 +329,8 @@ static int membarrier_register_private_expedited(int flags)
return 0;
if (flags & MEMBARRIER_FLAG_SYNC_CORE)
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)
@@ -311,7 +343,10 @@ static int membarrier_register_private_expedited(int flags)
/**
* 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.
+ * @flags: Currently needs to be 0 for all commands other than
+ * MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ: in the latter
+ * case it indicates the CPU on which to interrupt (= restart)
+ * the RSEQ critical section, or -1 to restart on all CPUs.
*
* If this system call is not implemented, -ENOSYS is returned. If the
* command specified does not exist, not available on the running
@@ -339,7 +374,7 @@ static int membarrier_register_private_expedited(int flags)
*/
SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
{
- if (unlikely(flags))
+ if (unlikely(flags) && cmd != MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ)
return -EINVAL;
switch (cmd) {
case MEMBARRIER_CMD_QUERY:
@@ -362,13 +397,17 @@ 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(0);
+ return membarrier_private_expedited(0, -1);
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,
-1);
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,
flags);
+ case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+ return
membarrier_register_private_expedited(MEMBARRIER_FLAG_RSEQ);
default:
return -EINVAL;
}
--
2.28.0.236.gb10cc79966-goog
