rseq/membarrier: Add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ

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.
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lkml.kernel.org/r/20200923233618.2572849-1-posk@google.com

include/linux/sched/mm.h

@@ -348,10 +348,13 @@ 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

include/linux/syscalls.h

@@ -974,7 +974,7 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename,
 			const char __user *const __user *argv,
 			const char __user *const __user *envp, int flags);
 asmlinkage long sys_userfaultfd(int flags);
-asmlinkage long sys_membarrier(int cmd, int flags);
+asmlinkage long sys_membarrier(int cmd, unsigned int flags, int cpu_id);
 asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
 asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in,
 				    int fd_out, loff_t __user *off_out,

include/uapi/linux/membarrier.h

@@ -114,6 +114,26 @@
  *                          If this command is not implemented by an
  *                          architecture, -EINVAL is returned.
  *                          Returns 0 on success.
+ * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+ *                          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 0; if @flags parameter is
+ *                          MEMBARRIER_CMD_FLAG_CPU,
+ *                          then this operation is performed only
+ *                          on CPU indicated by @cpu_id. 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.
@@ -131,9 +151,15 @@ 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,
 };
 
+enum membarrier_cmd_flag {
+	MEMBARRIER_CMD_FLAG_CPU		= (1 << 0),
+};
+
 #endif /* _UAPI_LINUX_MEMBARRIER_H */

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			\
@@ -30,6 +38,11 @@ static void ipi_mb(void *info)
 	smp_mb();	/* IPIs should be serializing but paranoid. */
 }
 
+static void ipi_rseq(void *info)
+{
+	rseq_preempt(current);
+}
+
 static void ipi_sync_rq_state(void *info)
 {
 	struct mm_struct *mm = (struct mm_struct *) info;
@@ -129,19 +142,27 @@ 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;
+	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(&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;
+		ipi_func = ipi_rseq;
 	} else {
+		WARN_ON_ONCE(flags);
 		if (!(atomic_read(&mm->membarrier_state) &
 		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
 			return -EPERM;
@@ -156,10 +177,28 @@ static int membarrier_private_expedited(int flags)
 	 */
 	smp_mb();	/* system call entry is not a mb. */
 
-	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+	if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
 	cpus_read_lock();
+
+	if (cpu_id >= 0) {
+		struct task_struct *p;
+
+		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) {
+			rcu_read_unlock();
+			goto out;
+		}
+		rcu_read_unlock();
+	} else {
+		int cpu;
+
 		rcu_read_lock();
 		for_each_online_cpu(cpu) {
 			struct task_struct *p;
@@ -179,11 +218,17 @@ static int membarrier_private_expedited(int flags)
 				__cpumask_set_cpu(cpu, tmpmask);
 		}
 		rcu_read_unlock();
+	}
 
 	preempt_disable();
-	smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+	if (cpu_id >= 0)
+		smp_call_function_single(cpu_id, ipi_func, NULL, 1);
+	else
+		smp_call_function_many(tmpmask, ipi_func, NULL, 1);
 	preempt_enable();
 
+out:
+	if (cpu_id < 0)
 		free_cpumask_var(tmpmask);
 	cpus_read_unlock();
 
@@ -283,11 +328,18 @@ 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 {
+		WARN_ON_ONCE(flags);
 	}
 
 	/*
@@ -299,6 +351,8 @@ 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 +365,14 @@ 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 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
@@ -337,10 +398,21 @@ static int membarrier_register_private_expedited(int flags)
  *        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)
 {
+	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:
 	{
@@ -362,13 +434,17 @@ 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, 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;
 	}