Re: [PATCH v5 17/23] iommu/vt-d: report non-recoverable faults to device
From: Lu Baolu
Date: Mon May 14 2018 - 04:17:42 EST
Hi,
On 05/12/2018 04:54 AM, Jacob Pan wrote:
> Currently, dmar fault IRQ handler does nothing more than rate
> limited printk, no critical hardware handling need to be done
> in IRQ context.
Not exactly. dmar_fault() needs to clear all the faults so that
the subsequent faults could be logged.
> For some use case such as vIOMMU, it might be useful to report
> non-recoverable faults outside host IOMMU subsystem. DMAR fault
> can come from both DMA and interrupt remapping which has to be
> set up early before threaded IRQ is available.
> This patch adds an option and a workqueue such that when faults
> are requested, DMAR fault IRQ handler can use the IOMMU fault
> reporting API to report.
>
> Signed-off-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
> Signed-off-by: Liu, Yi L <yi.l.liu@xxxxxxxxxxxxxxx>
> Signed-off-by: Ashok Raj <ashok.raj@xxxxxxxxx>
> ---
> drivers/iommu/dmar.c | 159 ++++++++++++++++++++++++++++++++++++++++++--
> drivers/iommu/intel-iommu.c | 6 +-
> include/linux/dmar.h | 2 +-
> include/linux/intel-iommu.h | 1 +
> 4 files changed, 159 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
> index 0b5b052..ef846e3 100644
> --- a/drivers/iommu/dmar.c
> +++ b/drivers/iommu/dmar.c
> @@ -1110,6 +1110,12 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
> return err;
> }
>
> +static inline void dmar_free_fault_wq(struct intel_iommu *iommu)
> +{
> + if (iommu->fault_wq)
> + destroy_workqueue(iommu->fault_wq);
> +}
> +
> static void free_iommu(struct intel_iommu *iommu)
> {
> if (intel_iommu_enabled) {
> @@ -1126,6 +1132,7 @@ static void free_iommu(struct intel_iommu *iommu)
> free_irq(iommu->irq, iommu);
> dmar_free_hwirq(iommu->irq);
> iommu->irq = 0;
> + dmar_free_fault_wq(iommu);
> }
>
> if (iommu->qi) {
> @@ -1554,6 +1561,31 @@ 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 <
> @@ -1634,11 +1666,91 @@ 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;
> + }
> +}
> +
> +struct dmar_fault_work {
> + struct work_struct fault_work;
> + struct intel_iommu *iommu;
> + u64 addr;
> + int type;
> + int fault_type;
> + enum intel_iommu_fault_reason reason;
> + u16 sid;
> +};
> +
> +static void report_fault_to_device(struct work_struct *work)
> +{
> + struct dmar_fault_work *dfw = container_of(work, struct dmar_fault_work,
> + fault_work);
> + struct iommu_fault_event event;
> + struct pci_dev *pdev;
> + u8 bus, devfn;
> +
> + memset(&event, 0, sizeof(struct iommu_fault_event));
> +
> + /* check if fault reason is permitted to report outside IOMMU */
> + if (!((1 << dfw->reason) & INTEL_IOMMU_FAULT_REASON_ALLOWED)) {
> + pr_debug("Fault reason %d not allowed to report to device\n",
> + dfw->reason);
No need to print this message. And how about moving this check ahead
before queue the work?
> + goto free_work;
> + }
> +
> + bus = PCI_BUS_NUM(dfw->sid);
> + devfn = PCI_DEVFN(PCI_SLOT(dfw->sid), PCI_FUNC(dfw->sid));
> + /*
> + * we need to check if the fault reporting is requested for the
> + * offending device.
> + */
> + pdev = pci_get_domain_bus_and_slot(dfw->iommu->segment, bus, devfn);
> + if (!pdev) {
> + pr_warn("No PCI device found for source ID %x\n", dfw->sid);
> + goto free_work;
> + }
> + /*
> + * unrecoverable fault is reported per IOMMU, notifier handler can
> + * resolve PCI device based on source ID.
> + */
> + event.reason = to_iommu_fault_reason(dfw->reason);
> + event.addr = dfw->addr;
> + event.type = IOMMU_FAULT_DMA_UNRECOV;
> + event.prot = dfw->type ? IOMMU_READ : IOMMU_WRITE;
> + dev_warn(&pdev->dev, "report device unrecoverable fault: %d, %x, %d\n",
> + event.reason, dfw->sid, event.type);
No need to print this warn message.
> + iommu_report_device_fault(&pdev->dev, &event);
> + pci_dev_put(pdev);
> +
> +free_work:
> + kfree(dfw);
> +}
> +
> static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
> u8 fault_reason, u16 source_id, unsigned long long addr)
> {
> const char *reason;
> int fault_type;
> + struct dmar_fault_work *dfw;
>
> reason = dmar_get_fault_reason(fault_reason, &fault_type);
>
> @@ -1647,11 +1759,29 @@ 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);
> + }
No need to add braces.
> +
> + dfw = kmalloc(sizeof(*dfw), GFP_ATOMIC);
> + if (!dfw)
> + return -ENOMEM;
> +
> + INIT_WORK(&dfw->fault_work, report_fault_to_device);
> + dfw->addr = addr;
> + dfw->type = type;
> + dfw->fault_type = fault_type;
> + dfw->reason = fault_reason;
> + dfw->sid = source_id;
> + dfw->iommu = iommu;
> + if (!queue_work(iommu->fault_wq, &dfw->fault_work)) {
Check whether this fault is allowed to report to device before
queuing the work.
> + kfree(dfw);
> + return -EBUSY;
> + }
> +
> return 0;
> }
>
> @@ -1731,10 +1861,28 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
> return IRQ_HANDLED;
> }
>
> -int dmar_set_interrupt(struct intel_iommu *iommu)
> +static int dmar_set_fault_wq(struct intel_iommu *iommu)
> +{
> + if (iommu->fault_wq)
> + return 0;
> +
> + iommu->fault_wq = alloc_ordered_workqueue(iommu->name, 0);
> + if (!iommu->fault_wq)
> + return -ENOMEM;
> +
> + return 0;
> +}
> +
> +int dmar_set_interrupt(struct intel_iommu *iommu, bool queue_fault)
> {
> int irq, ret;
>
> + /* fault can be reported back to device drivers via a wq */
> + if (queue_fault) {
> + ret = dmar_set_fault_wq(iommu);
> + if (ret)
> + pr_err("Failed to create fault handling workqueue\n");
> + }
> /*
> * Check if the fault interrupt is already initialized.
> */
> @@ -1748,10 +1896,11 @@ int dmar_set_interrupt(struct intel_iommu *iommu)
> pr_err("No free IRQ vectors\n");
> return -EINVAL;
> }
> -
> ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu);
> - if (ret)
> + if (ret) {
> pr_err("Can't request irq\n");
> + dmar_free_fault_wq(iommu);
> + }
> return ret;
> }
>
> @@ -1765,7 +1914,7 @@ int __init enable_drhd_fault_handling(void)
> */
> for_each_iommu(iommu, drhd) {
> u32 fault_status;
> - int ret = dmar_set_interrupt(iommu);
> + int ret = dmar_set_interrupt(iommu, false);
>
> if (ret) {
> pr_err("DRHD %Lx: failed to enable fault, interrupt, ret %d\n",
> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
> index 684bd98..3949b3cf 100644
> --- a/drivers/iommu/intel-iommu.c
> +++ b/drivers/iommu/intel-iommu.c
> @@ -3401,10 +3401,10 @@ static int __init init_dmars(void)
> goto free_iommu;
> }
> #endif
> - ret = dmar_set_interrupt(iommu);
> + ret = dmar_set_interrupt(iommu, true);
> +
> if (ret)
> goto free_iommu;
> -
> if (!translation_pre_enabled(iommu))
> iommu_enable_translation(iommu);
>
> @@ -4291,7 +4291,7 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
> goto disable_iommu;
> }
> #endif
> - ret = dmar_set_interrupt(iommu);
> + ret = dmar_set_interrupt(iommu, true);
> if (ret)
> goto disable_iommu;
>
> diff --git a/include/linux/dmar.h b/include/linux/dmar.h
> index e2433bc..21f2162 100644
> --- a/include/linux/dmar.h
> +++ b/include/linux/dmar.h
> @@ -278,7 +278,7 @@ extern void dmar_msi_unmask(struct irq_data *data);
> extern void dmar_msi_mask(struct irq_data *data);
> extern void dmar_msi_read(int irq, struct msi_msg *msg);
> extern void dmar_msi_write(int irq, struct msi_msg *msg);
> -extern int dmar_set_interrupt(struct intel_iommu *iommu);
> +extern int dmar_set_interrupt(struct intel_iommu *iommu, bool queue_fault);
> extern irqreturn_t dmar_fault(int irq, void *dev_id);
> extern int dmar_alloc_hwirq(int id, int node, void *arg);
> extern void dmar_free_hwirq(int irq);
> diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
> index 5ac0c28..b3a26c7 100644
> --- a/include/linux/intel-iommu.h
> +++ b/include/linux/intel-iommu.h
> @@ -472,6 +472,7 @@ struct intel_iommu {
> struct iommu_device iommu; /* IOMMU core code handle */
> int node;
> u32 flags; /* Software defined flags */
> + struct workqueue_struct *fault_wq; /* Reporting IOMMU fault to device */
> };
>
> /* PCI domain-device relationship */
Best regards,
Lu Baolu