lkml.org 
[lkml]   [2017]   [Dec]   [5]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCH v3 12/16] iommu/vt-d: report unrecoverable device faults
From
Date
Hi,

On 11/18/2017 02:55 AM, Jacob Pan wrote:
> Currently, when device DMA faults are detected by IOMMU the fault
> reasons are printed but the driver of the offending device is

"... but the driver of the offending device is not involved in ..."

Best regards,
Lu Baolu

> involved in fault handling.
> This patch uses per device fault reporting API to send fault event
> data for further processing.
> Offending device is identified by the source ID in VT-d fault reason
> report registers.
>
> Signed-off-by: Liu, Yi L <yi.l.liu@linux.intel.com>
> Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
> Signed-off-by: Ashok Raj <ashok.raj@intel.com>
> ---
> drivers/iommu/dmar.c | 94 +++++++++++++++++++++++++++++++++++++++++++++++++++-
> 1 file changed, 93 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
> index 38ee91b..b1f67fc2 100644
> --- a/drivers/iommu/dmar.c
> +++ b/drivers/iommu/dmar.c
> @@ -1555,6 +1555,31 @@ static const char *irq_remap_fault_reasons[] =
> "Blocked an interrupt request due to source-id verification failure",
> };
>
> +/* fault data and status */
> +enum intel_iommu_fault_reason {
> + INTEL_IOMMU_FAULT_REASON_SW,
> + INTEL_IOMMU_FAULT_REASON_ROOT_NOT_PRESENT,
> + INTEL_IOMMU_FAULT_REASON_CONTEXT_NOT_PRESENT,
> + INTEL_IOMMU_FAULT_REASON_CONTEXT_INVALID,
> + INTEL_IOMMU_FAULT_REASON_BEYOND_ADDR_WIDTH,
> + INTEL_IOMMU_FAULT_REASON_PTE_WRITE_ACCESS,
> + INTEL_IOMMU_FAULT_REASON_PTE_READ_ACCESS,
> + INTEL_IOMMU_FAULT_REASON_NEXT_PT_INVALID,
> + INTEL_IOMMU_FAULT_REASON_ROOT_ADDR_INVALID,
> + INTEL_IOMMU_FAULT_REASON_CONTEXT_PTR_INVALID,
> + INTEL_IOMMU_FAULT_REASON_NONE_ZERO_RTP,
> + INTEL_IOMMU_FAULT_REASON_NONE_ZERO_CTP,
> + INTEL_IOMMU_FAULT_REASON_NONE_ZERO_PTE,
> + NR_INTEL_IOMMU_FAULT_REASON,
> +};
> +
> +/* fault reasons that are allowed to be reported outside IOMMU subsystem */
> +#define INTEL_IOMMU_FAULT_REASON_ALLOWED \
> + ((1ULL << INTEL_IOMMU_FAULT_REASON_BEYOND_ADDR_WIDTH) | \
> + (1ULL << INTEL_IOMMU_FAULT_REASON_PTE_WRITE_ACCESS) | \
> + (1ULL << INTEL_IOMMU_FAULT_REASON_PTE_READ_ACCESS))
> +
> +
> static const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
> {
> if (fault_reason >= 0x20 && (fault_reason - 0x20 <
> @@ -1635,6 +1660,69 @@ void dmar_msi_read(int irq, struct msi_msg *msg)
> raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
> }
>
> +static enum iommu_fault_reason to_iommu_fault_reason(u8 reason)
> +{
> + if (reason >= NR_INTEL_IOMMU_FAULT_REASON) {
> + pr_warn("unknown DMAR fault reason %d\n", reason);
> + return IOMMU_FAULT_REASON_UNKNOWN;
> + }
> + switch (reason) {
> + case INTEL_IOMMU_FAULT_REASON_SW:
> + case INTEL_IOMMU_FAULT_REASON_ROOT_NOT_PRESENT:
> + case INTEL_IOMMU_FAULT_REASON_CONTEXT_NOT_PRESENT:
> + case INTEL_IOMMU_FAULT_REASON_CONTEXT_INVALID:
> + case INTEL_IOMMU_FAULT_REASON_BEYOND_ADDR_WIDTH:
> + case INTEL_IOMMU_FAULT_REASON_ROOT_ADDR_INVALID:
> + case INTEL_IOMMU_FAULT_REASON_CONTEXT_PTR_INVALID:
> + return IOMMU_FAULT_REASON_INTERNAL;
> + case INTEL_IOMMU_FAULT_REASON_NEXT_PT_INVALID:
> + case INTEL_IOMMU_FAULT_REASON_PTE_WRITE_ACCESS:
> + case INTEL_IOMMU_FAULT_REASON_PTE_READ_ACCESS:
> + return IOMMU_FAULT_REASON_PERMISSION;
> + default:
> + return IOMMU_FAULT_REASON_UNKNOWN;
> + }
> +}
> +
> +static void report_fault_to_device(struct intel_iommu *iommu, u64 addr, int type,
> + int fault_type, enum intel_iommu_fault_reason reason, u16 sid)
> +{
> + struct iommu_fault_event event;
> + struct pci_dev *pdev;
> + u8 bus, devfn;
> +
> + /* check if fault reason is worth reporting outside IOMMU */
> + if (!((1 << reason) & INTEL_IOMMU_FAULT_REASON_ALLOWED)) {
> + pr_debug("Fault reason %d not allowed to report to device\n",
> + reason);
> + return;
> + }
> +
> + bus = PCI_BUS_NUM(sid);
> + devfn = PCI_DEVFN(PCI_SLOT(sid), PCI_FUNC(sid));
> + /*
> + * we need to check if the fault reporting is requested for the
> + * offending device.
> + */
> + pdev = pci_get_bus_and_slot(bus, devfn);
> + if (!pdev) {
> + pr_warn("No PCI device found for source ID %x\n", sid);
> + return;
> + }
> + /*
> + * unrecoverable fault is reported per IOMMU, notifier handler can
> + * resolve PCI device based on source ID.
> + */
> + event.reason = to_iommu_fault_reason(reason);
> + event.addr = addr;
> + event.type = IOMMU_FAULT_DMA_UNRECOV;
> + event.prot = type ? IOMMU_READ : IOMMU_WRITE;
> + dev_warn(&pdev->dev, "report device unrecoverable fault: %d, %x, %d\n",
> + event.reason, sid, event.type);
> + iommu_report_device_fault(&pdev->dev, &event);
> + pci_dev_put(pdev);
> +}
> +
> static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
> u8 fault_reason, u16 source_id, unsigned long long addr)
> {
> @@ -1648,11 +1736,15 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
> source_id >> 8, PCI_SLOT(source_id & 0xFF),
> PCI_FUNC(source_id & 0xFF), addr >> 48,
> fault_reason, reason);
> - else
> + else {
> pr_err("[%s] Request device [%02x:%02x.%d] fault addr %llx [fault reason %02d] %s\n",
> type ? "DMA Read" : "DMA Write",
> source_id >> 8, PCI_SLOT(source_id & 0xFF),
> PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
> + }
> + report_fault_to_device(iommu, addr, type, fault_type,
> + fault_reason, source_id);
> +
> return 0;
> }
>

\
 
 \ /
  Last update: 2017-12-05 07:35    [W:0.294 / U:0.248 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site