4.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Marc Zyngier marc.zyngier@arm.com
[ Upstream commit 1aa55ca9b14af6cfd987ce4fdaf548f7067a5d07 ]
Enabling the interrupt early, before power has been applied to the device, can result in an interrupt being delivered too early if:
- the IOMMU shares an interrupt with a VOP - the VOP has a pending interrupt (after a kexec, for example)
In these conditions, we end-up taking the interrupt without the IOMMU being ready to handle the interrupt (not powered on).
Moving the interrupt request past the pm_runtime_enable() call makes sure we can at least access the IOMMU registers. Note that this is only a partial fix, and that the VOP interrupt will still be screaming until the VOP driver kicks in, which advocates for a more synchronized interrupt enabling/disabling approach.
Fixes: 0f181d3cf7d98 ("iommu/rockchip: Add runtime PM support") Reviewed-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Marc Zyngier marc.zyngier@arm.com Signed-off-by: Olof Johansson olof@lixom.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iommu/rockchip-iommu.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-)
--- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -1161,17 +1161,6 @@ static int rk_iommu_probe(struct platfor if (iommu->num_mmu == 0) return PTR_ERR(iommu->bases[0]);
- i = 0; - while ((irq = platform_get_irq(pdev, i++)) != -ENXIO) { - if (irq < 0) - return irq; - - err = devm_request_irq(iommu->dev, irq, rk_iommu_irq, - IRQF_SHARED, dev_name(dev), iommu); - if (err) - return err; - } - iommu->reset_disabled = device_property_read_bool(dev, "rockchip,disable-mmu-reset");
@@ -1228,6 +1217,19 @@ static int rk_iommu_probe(struct platfor
pm_runtime_enable(dev);
+ i = 0; + while ((irq = platform_get_irq(pdev, i++)) != -ENXIO) { + if (irq < 0) + return irq; + + err = devm_request_irq(iommu->dev, irq, rk_iommu_irq, + IRQF_SHARED, dev_name(dev), iommu); + if (err) { + pm_runtime_disable(dev); + goto err_remove_sysfs; + } + } + return 0; err_remove_sysfs: iommu_device_sysfs_remove(&iommu->iommu);