From: Zenghui Yu <yuzenghui@xxxxxxxxxx> In GICv4.1, we emulate a guest-issued INVALL command by a direct write to GICR_INVALLR. Before we finish the emulation and go back to guest, let's make sure the physical invalidate operation is actually completed and no stale data will be left in redistributor. Per the specification, this can be achieved by polling the GICR_SYNCR.Busy bit (to zero). Signed-off-by: Zenghui Yu <yuzenghui@xxxxxxxxxx> Signed-off-by: Marc Zyngier <maz@xxxxxxxxxx> Reviewed-by: Eric Auger <eric.auger@xxxxxxxxxx> Link: https://lore.kernel.org/r/20200302092145.899-1-yuzenghui@xxxxxxxxxx Link: https://lore.kernel.org/r/20200304203330.4967-5-maz@xxxxxxxxxx --- drivers/irqchip/irq-gic-v3-its.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 1af713990123..c84370245bea 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3827,6 +3827,8 @@ static void its_vpe_4_1_invall(struct its_vpe *vpe) /* Target the redistributor this vPE is currently known on */ rdbase = per_cpu_ptr(gic_rdists->rdist, vpe->col_idx)->rd_base; gic_write_lpir(val, rdbase + GICR_INVALLR); + + wait_for_syncr(rdbase); } static int its_vpe_4_1_set_vcpu_affinity(struct irq_data *d, void *vcpu_info) -- 2.20.1
