From d4990a46485f2f6592ae29f2b822043dbdeae15d Mon Sep 17 00:00:00 2001
From: Sean Anderson <seanga2@gmail.com>
Date: Mon, 21 Sep 2020 07:51:36 -0400
Subject: [PATCH] riscv: Match memory barriers between send_ipi_many and
handle_ipi
Without a matching barrier on the write side, the barrier in handle_ipi
does nothing. It was entirely possible for the boot hart to write to addr,
arg0, and arg1 *after* sending the IPI, because there was no barrier on the
sending side.
Fixes: 90ae281437 ("riscv: add option to wait for ack from secondary harts in smp functions")
Signed-off-by: Sean Anderson <seanga2@gmail.com>
Reviewed-by: Bin Meng <bin.meng@windriver.com>
Reviewed-by: Rick Chen <rick@andestech.com>
Reviewed-by: Leo Liang <ycliang@andestech.com>
---
arch/riscv/lib/smp.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/riscv/lib/smp.c b/arch/riscv/lib/smp.c
index ac22136314..ab6d8bd7fa 100644
--- a/arch/riscv/lib/smp.c
+++ b/arch/riscv/lib/smp.c
@@ -54,6 +54,8 @@ static int send_ipi_many(struct ipi_data *ipi, int wait)
gd->arch.ipi[reg].arg0 = ipi->arg0;
gd->arch.ipi[reg].arg1 = ipi->arg1;
+ __smp_mb();
+
ret = riscv_send_ipi(reg);
if (ret) {
pr_err("Cannot send IPI to hart %d\n", reg);
--
2.39.5