[RFC PATCH v3] membarrier: provide core serialization
From: Mathieu Desnoyers
Date: Fri Sep 01 2017 - 12:10:25 EST
Add a new MEMBARRIER_FLAG_SYNC_CORE flag to the membarrier
system call. It allows membarrier to issue core serializing barriers in
addition to memory barriers on target threads whenever a membarrier
command is performed.
It is relevant for reclaim of JIT code, which requires to issue core
serializing barriers on all threads running on behalf of a process
after ensuring the old code is not visible anymore, before re-using
memory for new code.
The new MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED used with
MEMBARRIER_FLAG_SYNC_CORE flag registers the current process as
requiring core serialization. It may block. It can be used to ensure
MEMBARRIER_CMD_PRIVATE_EXPEDITED never blocks, even the first time it is
invoked by a process with the MEMBARRIER_FLAG_SYNC_CORE flag.
* Scheduler Overhead Benchmarks
Intel(R) Xeon(R) CPU E5-2630 v3 @ 2.40GHz
Linux v4.13-rc6
Inter-thread scheduling
taskset 01 ./perf bench sched pipe -T
Avg. usecs/op Std.Dev. usecs/op
Before this change: 2.55 0.10
With this change: 2.49 0.08
SYNC_CORE processes: 2.70 0.10
Inter-process scheduling
taskset 01 ./perf bench sched pipe
Before this change: 2.93 0.13
With this change: 2.93 0.13
SYNC_CORE processes: 3.20 0.06
Changes since v2:
- Rename MEMBARRIER_CMD_REGISTER_SYNC_CORE to
MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED,
- Introduce the "MEMBARRIER_FLAG_SYNC_CORE" flag.
- Introduce CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE, only implemented by
x86 32/64 initially.
- Introduce arch_membarrier_user_icache_flush, a no-op on x86 32/64,
which can be implemented on architectures with incoherent data and
instruction caches. It is associated with
CONFIG_ARCH_HAS_MEMBARRIER_USER_ICACHE_FLUSH.
- Introduce membarrier_sync_core_active counter, used for the shared
system-wide membarrier with MEMBARRIER_FLAG_SYNC_CORE flag. If set, it
issues sync_core on sched_out.
- The membarrier_sync_core per-thread flag still issues a sync_core()
on sched_out, but now issues both sync_core and icache flush on
sched_in, only when the current->mm changes between prev and next.
Changes since v1:
- Add missing MEMBARRIER_CMD_REGISTER_SYNC_CORE header documentation,
- Add benchmarks to commit message.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
CC: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CC: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
CC: Boqun Feng <boqun.feng@xxxxxxxxx>
CC: Andrew Hunter <ahh@xxxxxxxxxx>
CC: Maged Michael <maged.michael@xxxxxxxxx>
CC: gromer@xxxxxxxxxx
CC: Avi Kivity <avi@xxxxxxxxxxxx>
CC: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
CC: Paul Mackerras <paulus@xxxxxxxxx>
CC: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
CC: Dave Watson <davejwatson@xxxxxx>
CC: Andy Lutomirski <luto@xxxxxxxxxx>
CC: Will Deacon <will.deacon@xxxxxxx>
CC: Hans Boehm <hboehm@xxxxxxxxxx>
---
arch/x86/Kconfig | 1 +
fs/exec.c | 1 +
include/linux/sched.h | 82 +++++++++++++++++++++++++
include/uapi/linux/membarrier.h | 32 ++++++++--
init/Kconfig | 6 ++
kernel/fork.c | 2 +
kernel/sched/core.c | 3 +
kernel/sched/membarrier.c | 133 +++++++++++++++++++++++++++++++++++-----
8 files changed, 240 insertions(+), 20 deletions(-)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 323cb065be5e..d39ae515632e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -62,6 +62,7 @@ config X86
select ARCH_HAS_STRICT_MODULE_RWX
select ARCH_HAS_UBSAN_SANITIZE_ALL
select ARCH_HAS_ZONE_DEVICE if X86_64
+ select ARCH_HAS_MEMBARRIER_SYNC_CORE
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
select ARCH_MIGHT_HAVE_PC_PARPORT
diff --git a/fs/exec.c b/fs/exec.c
index 62175cbcc801..a4ab3253bac7 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1794,6 +1794,7 @@ static int do_execveat_common(int fd, struct filename *filename,
/* execve succeeded */
current->fs->in_exec = 0;
current->in_execve = 0;
+ membarrier_execve(current);
acct_update_integrals(current);
task_numa_free(current);
free_bprm(bprm);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8337e2db0bb2..113d9c03a21c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1086,6 +1086,9 @@ struct task_struct {
/* Used by LSM modules for access restriction: */
void *security;
#endif
+#ifdef CONFIG_MEMBARRIER
+ int membarrier_sync_core;
+#endif
/*
* New fields for task_struct should be added above here, so that
@@ -1623,4 +1626,83 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
#define TASK_SIZE_OF(tsk) TASK_SIZE
#endif
+#ifdef CONFIG_ARCH_HAS_MEMBARRIER_USER_ICACHE_FLUSH
+/*
+ * Architectures with incoherent data and instruction caches are
+ * required to implement arch_membarrier_user_icache_flush() if they
+ * want to support the MEMBARRIER_FLAG_SYNC_CORE flag.
+ */
+extern void arch_membarrier_user_icache_flush(void);
+#else
+static inline void arch_membarrier_user_icache_flush(void)
+{
+}
+#endif
+
+#if defined(CONFIG_MEMBARRIER) && defined(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE)
+extern atomic_long_t membarrier_sync_core_active;
+
+static inline void membarrier_fork(struct task_struct *t,
+ unsigned long clone_flags)
+{
+ /*
+ * Coherence of membarrier_sync_core against thread fork is
+ * protected by siglock. membarrier_fork is called with siglock
+ * held.
+ */
+ t->membarrier_sync_core = current->membarrier_sync_core;
+}
+static inline void membarrier_execve(struct task_struct *t)
+{
+ t->membarrier_sync_core = 0;
+}
+static inline void membarrier_sched_out(struct task_struct *t)
+{
+ /*
+ * Core serialization is performed before the memory barrier
+ * preceding the store to rq->curr. A non-zero sync_core_active
+ * implies that a core serializing shared membarrier is in
+ * progress.
+ */
+ if (unlikely(READ_ONCE(t->membarrier_sync_core)
+ || atomic_long_read(&membarrier_sync_core_active)))
+ sync_core();
+ /*
+ * Flushing icache on each scheduler entry when a shared
+ * membarrier requiring core serialization is in progress.
+ */
+ if (unlikely(atomic_long_read(&membarrier_sync_core_active)))
+ arch_membarrier_user_icache_flush();
+}
+static inline void membarrier_sched_in(struct task_struct *prev,
+ struct task_struct *next)
+{
+ /*
+ * Core serialization is performed after the memory barrier
+ * following the store to rq->curr.
+ */
+ if (unlikely(READ_ONCE(next->membarrier_sync_core))) {
+ if (unlikely(prev->mm != next->mm)) {
+ sync_core();
+ arch_membarrier_user_icache_flush();
+ }
+ }
+}
+#else
+static inline void membarrier_fork(struct task_struct *t,
+ unsigned long clone_flags)
+{
+}
+static inline void membarrier_execve(struct task_struct *t)
+{
+}
+static inline void membarrier_sched_out(struct task_struct *t)
+{
+}
+static inline void membarrier_sched_in(struct task_struct *prev,
+ struct task_struct *next)
+{
+}
+#endif
+
#endif
diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h
index 6d47b3249d8a..4c8682026500 100644
--- a/include/uapi/linux/membarrier.h
+++ b/include/uapi/linux/membarrier.h
@@ -54,19 +54,41 @@
* same processes as the caller thread. This
* command returns 0. The "expedited" commands
* complete faster than the non-expedited ones,
- * they never block, but have the downside of
- * causing extra overhead.
+ * they usually never block, but have the
+ * downside of causing extra overhead. The only
+ * case where it can block is the first time it
+ * is called by a process with the
+ * MEMBARRIER_FLAG_SYNC_CORE flag, if there has
+ * not been any prior registration of that
+ * process with
+ * MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED
+ * and the same flag.
+ * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
+ * When used with MEMBARRIER_FLAG_SYNC_CORE,
+ * register the current process as requiring
+ * core serialization when a private expedited
+ * membarrier is issued. It may block. It can
+ * be used to ensure
+ * MEMBARRIER_CMD_PRIVATE_EXPEDITED never
+ * blocks, even the first time it is invoked by
+ * a process with the MEMBARRIER_FLAG_SYNC_CORE
+ * flag.
*
* Command to be passed to the membarrier system call. The commands need to
* be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to
* the value 0.
*/
enum membarrier_cmd {
- MEMBARRIER_CMD_QUERY = 0,
- MEMBARRIER_CMD_SHARED = (1 << 0),
+ MEMBARRIER_CMD_QUERY = 0,
+ MEMBARRIER_CMD_SHARED = (1 << 0),
/* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */
/* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */
- MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3),
+ MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3),
+ MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4),
+};
+
+enum membarrier_flags {
+ MEMBARRIER_FLAG_SYNC_CORE = (1 << 0),
};
#endif /* _UAPI_LINUX_MEMBARRIER_H */
diff --git a/init/Kconfig b/init/Kconfig
index 8514b25db21c..e74baef9f347 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -615,6 +615,12 @@ config ARCH_SUPPORTS_INT128
config ARCH_WANT_NUMA_VARIABLE_LOCALITY
bool
+# For architectures implementing membarrier core synchronization,
+# required by the membarrier sync_core registration.
+#
+config ARCH_HAS_MEMBARRIER_SYNC_CORE
+ bool
+
config NUMA_BALANCING
bool "Memory placement aware NUMA scheduler"
depends on ARCH_SUPPORTS_NUMA_BALANCING
diff --git a/kernel/fork.c b/kernel/fork.c
index e075b7780421..1d44d7250431 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1840,6 +1840,8 @@ static __latent_entropy struct task_struct *copy_process(
*/
copy_seccomp(p);
+ membarrier_fork(p, clone_flags);
+
/*
* Process group and session signals need to be delivered to just the
* parent before the fork or both the parent and the child after the
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d57553551ad6..98aac5a44604 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3292,6 +3292,8 @@ static void __sched notrace __schedule(bool preempt)
local_irq_disable();
rcu_note_context_switch(preempt);
+ membarrier_sched_out(prev);
+
/*
* Make sure that signal_pending_state()->signal_pending() below
* can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
@@ -3364,6 +3366,7 @@ static void __sched notrace __schedule(bool preempt)
/* Also unlocks the rq: */
rq = context_switch(rq, prev, next, &rf);
+ membarrier_sched_in(prev, next);
} else {
rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
rq_unlock_irq(rq, &rf);
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 7eec6914d2d2..8c8a25e17a50 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -18,6 +18,7 @@
#include <linux/membarrier.h>
#include <linux/tick.h>
#include <linux/cpumask.h>
+#include <linux/atomic.h>
#include "sched.h" /* for cpu_rq(). */
@@ -25,22 +26,118 @@
* 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)
+#define MEMBARRIER_CMD_BITMASK \
+ (MEMBARRIER_CMD_SHARED \
+ | MEMBARRIER_CMD_PRIVATE_EXPEDITED \
+ | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED)
+
+#ifdef CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE
+atomic_long_t membarrier_sync_core_active;
+
+static void membarrier_shared_sync_core_begin(int flags)
+{
+ if (flags & MEMBARRIER_FLAG_SYNC_CORE)
+ atomic_long_inc(&membarrier_sync_core_active);
+}
+
+static void membarrier_shared_sync_core_end(int flags)
+{
+ if (flags & MEMBARRIER_FLAG_SYNC_CORE)
+ atomic_long_dec(&membarrier_sync_core_active);
+}
+
+static int membarrier_register_private_expedited_sync_core(void)
+{
+ struct task_struct *p = current, *t;
+
+ if (READ_ONCE(p->membarrier_sync_core))
+ return 0;
+ if (get_nr_threads(p) == 1) {
+ p->membarrier_sync_core = 1;
+ return 0;
+ }
+
+ /*
+ * Coherence of membarrier_sync_core against thread fork is
+ * protected by siglock.
+ */
+ spin_lock(&p->sighand->siglock);
+ for_each_thread(p, t)
+ WRITE_ONCE(t->membarrier_sync_core, 1);
+ spin_unlock(&p->sighand->siglock);
+ /*
+ * Ensure all future scheduler execution will observe the new
+ * membarrier_sync_core state for this process.
+ */
+ synchronize_sched();
+ return 0;
+}
+static void membarrier_sync_core(void)
+{
+ sync_core();
+}
+#else
+static void membarrier_shared_sync_core_begin(int flags)
+{
+}
+static void membarrier_shared_sync_core_end(int flags)
+{
+}
+static int membarrier_register_private_expedited_sync_core(void)
+{
+ return -EINVAL;
+}
+static void membarrier_sync_core(void)
+{
+}
+#endif
+
+static int membarrier_shared(int flags)
+{
+ if (unlikely(flags & ~MEMBARRIER_FLAG_SYNC_CORE))
+ return -EINVAL;
+ /* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */
+ if (tick_nohz_full_enabled())
+ return -EINVAL;
+ if (num_online_cpus() == 1)
+ return 0;
+
+ membarrier_shared_sync_core_begin(flags);
+ synchronize_sched();
+ membarrier_shared_sync_core_end(flags);
+
+ return 0;
+}
static void ipi_mb(void *info)
{
- smp_mb(); /* IPIs should be serializing but paranoid. */
+ /* IPIs should be serializing but paranoid. */
+ smp_mb();
+ membarrier_sync_core();
+ arch_membarrier_user_icache_flush();
}
-static void membarrier_private_expedited(void)
+static int membarrier_private_expedited(int flags)
{
int cpu;
bool fallback = false;
cpumask_var_t tmpmask;
+ if (unlikely(flags & ~MEMBARRIER_FLAG_SYNC_CORE))
+ return -EINVAL;
+ /*
+ * Do the process registration ourself if it has not been
+ * performed by an explicit register command.
+ */
+ if (unlikely(flags & MEMBARRIER_FLAG_SYNC_CORE)) {
+ int ret;
+
+ ret = membarrier_register_private_expedited_sync_core();
+ if (ret)
+ return ret;
+ }
if (num_online_cpus() == 1 || get_nr_threads(current) == 1)
- return;
+ return 0;
/*
* Matches memory barriers around rq->curr modification in
@@ -94,6 +191,16 @@ static void membarrier_private_expedited(void)
* rq->curr modification in scheduler.
*/
smp_mb(); /* exit from system call is not a mb */
+ return 0;
+}
+
+static int membarrier_register_private_expedited(int flags)
+{
+ if (unlikely(flags & ~MEMBARRIER_FLAG_SYNC_CORE))
+ return -EINVAL;
+ if (flags & MEMBARRIER_FLAG_SYNC_CORE)
+ return membarrier_register_private_expedited_sync_core();
+ return 0;
}
/**
@@ -125,27 +232,23 @@ static void membarrier_private_expedited(void)
*/
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 (unlikely(flags))
+ return -EINVAL;
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;
+ return membarrier_shared(flags);
case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
- membarrier_private_expedited();
- return 0;
+ return membarrier_private_expedited(flags);
+ case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
+ return membarrier_register_private_expedited(flags);
default:
return -EINVAL;
}
--
2.11.0