Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 46c142b..cc7cd51 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -18,12 +18,21 @@
 #define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK	0
 #endif
 
+#ifdef CONFIG_RSEQ
+#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK		\
+	(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ			\
+	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ)
+#else
+#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK	0
+#endif
+
 #define MEMBARRIER_CMD_BITMASK						\
 	(MEMBARRIER_CMD_GLOBAL | MEMBARRIER_CMD_GLOBAL_EXPEDITED	\
 	| MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED			\
 	| MEMBARRIER_CMD_PRIVATE_EXPEDITED				\
 	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED			\
-	| MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK)
+	| MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK		\
+	| MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
 
 static void ipi_mb(void *info)
 {
@@ -47,6 +56,19 @@
 	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);
+}
+
 static void ipi_sync_rq_state(void *info)
 {
 	struct mm_struct *mm = (struct mm_struct *) info;
@@ -146,27 +168,35 @@
 	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;
 		ipi_func = ipi_sync_core;
+	} 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;
 	}
 
-	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;
 
 	/*
@@ -175,35 +205,73 @@
 	 */
 	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();
-	rcu_read_lock();
-	for_each_online_cpu(cpu) {
+
+	if (cpu_id >= 0) {
 		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);
+		if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_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;
+
+			p = rcu_dereference(cpu_rq(cpu)->curr);
+			if (p && p->mm == mm)
+				__cpumask_set_cpu(cpu, tmpmask);
+		}
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
 
-	preempt_disable();
-	smp_call_function_many(tmpmask, ipi_func, NULL, 1);
-	preempt_enable();
+	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 {
+		/*
+		 * 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);
+		}
+	}
 
-	free_cpumask_var(tmpmask);
+out:
+	if (cpu_id < 0)
+		free_cpumask_var(tmpmask);
 	cpus_read_unlock();
 
 	/*
@@ -248,7 +316,7 @@
 
 	/*
 	 * For each cpu runqueue, if the task's mm match @mm, ensure that all
-	 * @mm's membarrier state set bits are also set in in the runqueue's
+	 * @mm's membarrier state set bits are also set in the runqueue's
 	 * membarrier state. This ensures that a runqueue scheduling
 	 * between threads which are users of @mm has its membarrier state
 	 * updated.
@@ -300,11 +368,18 @@
 	    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);
 	}
 
 	/*
@@ -316,6 +391,8 @@
 		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)
@@ -327,8 +404,15 @@
 
 /**
  * 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.
+ * @cmd:    Takes command values defined in enum membarrier_cmd.
+ * @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
@@ -354,10 +438,21 @@
  *        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)
 {
-	if (unlikely(flags))
-		return -EINVAL;
+	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:
 	{
@@ -379,13 +474,17 @@
 	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;
 	}