x86 has a missing core serializing instruction in migration scenarios.
Given that x86-32 can return to user-space with sysexit, and x86-64
through sysretq and sysretl, which are not core serializing, the
following user-space self-modifiying code (JIT) scenario can occur:
CPU 0 CPU 1
User-space self-modify code
Preempted
migrated ->
scheduler selects task
Return to user-space (iret or sysexit)
User-space issues sync_core()
<- migrated
scheduler selects task
Return to user-space (sysexit)
jump to modified code
Run modified code without sync_core() -> bug.
This migration pattern can return to user-space through sysexit,
sysretl, or sysretq, which are not core serializing, and therefore
breaks sequential consistency expectations from a single-threaded
process.
Fix this issue by introducing sync_core_before_usermode(), invoked the
first time a runqueue finishes a task switch after receiving a migrated
thread.
Architectures defining the sync_core_before_usermode() static inline
need to define ARCH_HAS_SYNC_CORE_BEFORE_USERMODE.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
CC: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CC: Andy Lutomirski <luto@xxxxxxxxxx>
CC: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
CC: Boqun Feng <boqun.feng@xxxxxxxxx>
CC: Andrew Hunter <ahh@xxxxxxxxxx>
CC: Maged Michael <maged.michael@xxxxxxxxx>
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: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
CC: Ingo Molnar <mingo@xxxxxxxxxx>
CC: "H. Peter Anvin" <hpa@xxxxxxxxx>
CC: Andrea Parri <parri.andrea@xxxxxxxxx>
CC: Russell King <linux@xxxxxxxxxxxxxxx>
CC: Greg Hackmann <ghackmann@xxxxxxxxxx>
CC: Will Deacon <will.deacon@xxxxxxx>
CC: David Sehr <sehr@xxxxxxxxxx>
CC: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
CC: x86@xxxxxxxxxx
CC: linux-arch@xxxxxxxxxxxxxxx
CC: stable@xxxxxxxxxx
---
Changes since v1:
- Fold patch introducing sync_core_before_usermode and the fix
into a single patch.
- CC stable@xxxxxxxxxx
---
arch/x86/Kconfig | 1 +
arch/x86/include/asm/processor.h | 10 ++++++++++
include/linux/processor.h | 6 ++++++
kernel/sched/core.c | 7 +++++++
kernel/sched/sched.h | 1 +
5 files changed, 25 insertions(+)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2fdb23313dd5..b27456f04cc6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -62,6 +62,7 @@ config X86
select ARCH_HAS_SG_CHAIN
select ARCH_HAS_STRICT_KERNEL_RWX
select ARCH_HAS_STRICT_MODULE_RWX
+ select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
select ARCH_HAS_UBSAN_SANITIZE_ALL
select ARCH_HAS_ZONE_DEVICE if X86_64
select ARCH_HAVE_NMI_SAFE_CMPXCHG
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index bdac19ab2488..6daf70a8c81c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -706,6 +706,16 @@ static inline void sync_core(void)
#endif
}
+/*
+ * Ensure that a core serializing instruction is issued before returning
+ * to user-mode. x86 implements return to user-space through sysexit,
+ * sysretl, and sysretq, which are not core serializing.
+ */
+static inline void sync_core_before_usermode(void)
+{
+ sync_core();
+}
+
extern void select_idle_routine(const struct cpuinfo_x86 *c);
extern void amd_e400_c1e_apic_setup(void);
diff --git a/include/linux/processor.h b/include/linux/processor.h
index dbc952eec869..7d12e6fa050e 100644
--- a/include/linux/processor.h
+++ b/include/linux/processor.h
@@ -68,4 +68,10 @@ do { \
#endif
+#ifndef ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
+static inline sync_core_before_usermode(void)
+{
+}
+#endif
+
#endif /* _LINUX_PROCESSOR_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d17c5da523a0..39c0bbe8f259 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -927,6 +927,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
rq_lock(rq, rf);
BUG_ON(task_cpu(p) != new_cpu);
+ rq->need_sync_core = 1;
enqueue_task(rq, p, 0);
p->on_rq = TASK_ON_RQ_QUEUED;
check_preempt_curr(rq, p, 0);
@@ -2654,6 +2655,12 @@ static struct rq *finish_task_switch(struct task_struct *prev)
* to use.
*/
smp_mb__after_unlock_lock();
+#ifdef CONFIG_SMP
+ if (unlikely(rq->need_sync_core)) {
+ sync_core_before_usermode();
+ rq->need_sync_core = 0;
+ }
+#endif
finish_lock_switch(rq, prev);
finish_arch_post_lock_switch();
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3b448ba82225..e02cc362637c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -734,6 +734,7 @@ struct rq {
/* For active balancing */
int active_balance;
int push_cpu;
+ int need_sync_core;
struct cpu_stop_work active_balance_work;
/* cpu of this runqueue: */
int cpu;
--
2.11.0
--
To unsubscribe from this list: send the line "unsubscribe linux-api" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
