membarrier: riscv: Add full memory barrier in switch_mm()

The membarrier system call requires a full memory barrier after storing
to rq->curr, before going back to user-space.  The barrier is only
needed when switching between processes: the barrier is implied by
mmdrop() when switching from kernel to userspace, and it's not needed
when switching from userspace to kernel.

Rely on the feature/mechanism ARCH_HAS_MEMBARRIER_CALLBACKS and on the
primitive membarrier_arch_switch_mm(), already adopted by the PowerPC
architecture, to insert the required barrier.

Fixes: fab957c ("RISC-V: Atomic and Locking Code")
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/r/20240131144936.29190-2-parri.andrea@gmail.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Author: andrea-parri

MAINTAINERS

@@ -14039,7 +14039,7 @@ M:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
 M:	"Paul E. McKenney" <paulmck@kernel.org>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
-F:	arch/powerpc/include/asm/membarrier.h
+F:	arch/*/include/asm/membarrier.h
 F:	include/uapi/linux/membarrier.h
 F:	kernel/sched/membarrier.c
 

arch/riscv/Kconfig

@@ -27,6 +27,7 @@ config RISCV
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_MMIOWB
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PMEM_API

arch/riscv/include/asm/membarrier.h

@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_RISCV_MEMBARRIER_H
+#define _ASM_RISCV_MEMBARRIER_H
+
+static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
+					     struct mm_struct *next,
+					     struct task_struct *tsk)
+{
+	/*
+	 * Only need the full barrier when switching between processes.
+	 * Barrier when switching from kernel to userspace is not
+	 * required here, given that it is implied by mmdrop(). Barrier
+	 * when switching from userspace to kernel is not needed after
+	 * store to rq->curr.
+	 */
+	if (IS_ENABLED(CONFIG_SMP) &&
+	    likely(!(atomic_read(&next->membarrier_state) &
+		     (MEMBARRIER_STATE_PRIVATE_EXPEDITED |
+		      MEMBARRIER_STATE_GLOBAL_EXPEDITED)) || !prev))
+		return;
+
+	/*
+	 * The membarrier system call requires a full memory barrier
+	 * after storing to rq->curr, before going back to user-space.
+	 * Matches a full barrier in the proximity of the membarrier
+	 * system call entry.
+	 */
+	smp_mb();
+}
+
+#endif /* _ASM_RISCV_MEMBARRIER_H */

arch/riscv/mm/context.c

@@ -323,6 +323,8 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	if (unlikely(prev == next))
 		return;
 
+	membarrier_arch_switch_mm(prev, next, task);
+
 	/*
 	 * Mark the current MM context as inactive, and the next as
 	 * active.  This is at least used by the icache flushing

kernel/sched/core.c

@@ -6709,8 +6709,9 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		 *
 		 * Here are the schemes providing that barrier on the
 		 * various architectures:
-		 * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
-		 *   switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
+		 * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC,
+		 *   RISC-V.  switch_mm() relies on membarrier_arch_switch_mm()
+		 *   on PowerPC and on RISC-V.
 		 * - finish_lock_switch() for weakly-ordered
 		 *   architectures where spin_unlock is a full barrier,
 		 * - switch_to() for arm64 (weakly-ordered, spin_unlock