From: Ethan Zhao Date: Tue, 5 Mar 2024 12:21:16 +0000 (+0800) Subject: iommu/vt-d: Improve ITE fault handling if target device isn't present X-Git-Tag: v6.9-rc1~153^2^5~6 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=80a9b50c0b9e297669a8a400eb35468cd87a9aed;p=thirdparty%2Fkernel%2Flinux.git iommu/vt-d: Improve ITE fault handling if target device isn't present Because surprise removal could happen anytime, e.g. user could request safe removal to EP(endpoint device) via sysfs and brings its link down to do surprise removal cocurrently. such aggressive cases would cause ATS invalidation request issued to non-existence target device, then deadly loop to retry that request after ITE fault triggered in interrupt context. this patch aims to optimize the ITE handling by checking the target device presence state to avoid retrying the timeout request blindly, thus avoid hard lockup or system hang. Devices TLB should only be invalidated when devices are in the iommu->device_rbtree (probed, not released) and present. Fixes: 6ba6c3a4cacf ("VT-d: add device IOTLB invalidation support") Reviewed-by: Dan Carpenter Signed-off-by: Ethan Zhao Link: https://lore.kernel.org/r/20240301080727.3529832-4-haifeng.zhao@linux.intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index d14797aabb7ad..36d7427b12026 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1273,6 +1273,8 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index) { u32 fault; int head, tail; + struct device *dev; + u64 iqe_err, ite_sid; struct q_inval *qi = iommu->qi; int shift = qi_shift(iommu); @@ -1317,6 +1319,13 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index) tail = readl(iommu->reg + DMAR_IQT_REG); tail = ((tail >> shift) - 1 + QI_LENGTH) % QI_LENGTH; + /* + * SID field is valid only when the ITE field is Set in FSTS_REG + * see Intel VT-d spec r4.1, section 11.4.9.9 + */ + iqe_err = dmar_readq(iommu->reg + DMAR_IQER_REG); + ite_sid = DMAR_IQER_REG_ITESID(iqe_err); + writel(DMA_FSTS_ITE, iommu->reg + DMAR_FSTS_REG); pr_info("Invalidation Time-out Error (ITE) cleared\n"); @@ -1326,6 +1335,19 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index) head = (head - 2 + QI_LENGTH) % QI_LENGTH; } while (head != tail); + /* + * If device was released or isn't present, no need to retry + * the ATS invalidate request anymore. + * + * 0 value of ite_sid means old VT-d device, no ite_sid value. + * see Intel VT-d spec r4.1, section 11.4.9.9 + */ + if (ite_sid) { + dev = device_rbtree_find(iommu, ite_sid); + if (!dev || !dev_is_pci(dev) || + !pci_device_is_present(to_pci_dev(dev))) + return -ETIMEDOUT; + } if (qi->desc_status[wait_index] == QI_ABORT) return -EAGAIN; }