On Thu, Jul 21, 2016 at 08:45:30PM +0300, Michael S. Tsirkin wrote:
> On Thu, Jul 14, 2016 at 01:56:22PM +0800, Peter Xu wrote:
> > This patch enables interrupt remapping for PCI devices.
> >
> > To play the trick, one memory region "iommu_ir" is added as child region
> > of the original iommu memory region, covering range 0xfeeXXXXX (which is
> > the address range for APIC). All the writes to this range will be taken
> > as MSI, and translation is carried out only when IR is enabled.
> >
> > Idea suggested by Paolo Bonzini.
> >
> > Signed-off-by: Peter Xu <pet...@redhat.com>
> > ---
> > hw/i386/intel_iommu.c | 241
> > +++++++++++++++++++++++++++++++++++++++++
> > hw/i386/intel_iommu_internal.h | 2 +
> > include/hw/i386/intel_iommu.h | 66 +++++++++++
> > 3 files changed, 309 insertions(+)
> >
> > diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
> > index 6a6cb3b..3d1b15d 100644
> > --- a/hw/i386/intel_iommu.c
> > +++ b/hw/i386/intel_iommu.c
> > @@ -1982,6 +1982,242 @@ static Property vtd_properties[] = {
> > DEFINE_PROP_END_OF_LIST(),
> > };
> >
> > +/* Read IRTE entry with specific index */
> > +static int vtd_irte_get(IntelIOMMUState *iommu, uint16_t index,
> > + VTD_IRTE *entry)
> > +{
> > + dma_addr_t addr = 0x00;
> > +
> > + addr = iommu->intr_root + index * sizeof(*entry);
> > + if (dma_memory_read(&address_space_memory, addr, entry,
> > + sizeof(*entry))) {
> > + VTD_DPRINTF(GENERAL, "error: fail to access IR root at 0x%"PRIx64
> > + " + %"PRIu16, iommu->intr_root, index);
> > + return -VTD_FR_IR_ROOT_INVAL;
> > + }
> > +
> > + if (!entry->present) {
> > + VTD_DPRINTF(GENERAL, "error: present flag not set in IRTE"
> > + " entry index %u value 0x%"PRIx64 " 0x%"PRIx64,
> > + index, le64_to_cpu(entry->data[1]),
> > + le64_to_cpu(entry->data[0]));
> > + return -VTD_FR_IR_ENTRY_P;
> > + }
> > +
> > + if (entry->__reserved_0 || entry->__reserved_1 || \
> > + entry->__reserved_2) {
> > + VTD_DPRINTF(GENERAL, "error: IRTE entry index %"PRIu16
> > + " reserved fields non-zero: 0x%"PRIx64 " 0x%"PRIx64,
> > + index, le64_to_cpu(entry->data[1]),
> > + le64_to_cpu(entry->data[0]));
> > + return -VTD_FR_IR_IRTE_RSVD;
> > + }
> > +
> > + /*
> > + * TODO: Check Source-ID corresponds to SVT (Source Validation
> > + * Type) bits
> > + */
> > +
> > + return 0;
> > +}
> > +
> > +/* Fetch IRQ information of specific IR index */
> > +static int vtd_remap_irq_get(IntelIOMMUState *iommu, uint16_t index,
> > VTDIrq *irq)
> > +{
> > + VTD_IRTE irte;
> > + int ret = 0;
> > +
> > + bzero(&irte, sizeof(irte));
> > +
> > + ret = vtd_irte_get(iommu, index, &irte);
> > + if (ret) {
> > + return ret;
> > + }
> > +
> > + irq->trigger_mode = irte.trigger_mode;
> > + irq->vector = irte.vector;
> > + irq->delivery_mode = irte.delivery_mode;
> > + /* Not support EIM yet: please refer to vt-d 9.10 DST bits */
> > +#define VTD_IR_APIC_DEST_MASK (0xff00ULL)
> > +#define VTD_IR_APIC_DEST_SHIFT (8)
> > + irq->dest = (le32_to_cpu(irte.dest_id) & VTD_IR_APIC_DEST_MASK) >> \
> > + VTD_IR_APIC_DEST_SHIFT;
> > + irq->dest_mode = irte.dest_mode;
> > + irq->redir_hint = irte.redir_hint;
> > +
> > + VTD_DPRINTF(IR, "remapping interrupt index %d: trig:%u,vec:%u,"
> > + "deliver:%u,dest:%u,dest_mode:%u", index,
> > + irq->trigger_mode, irq->vector, irq->delivery_mode,
> > + irq->dest, irq->dest_mode);
> > +
> > + return 0;
> > +}
> > +
> > +/* Generate one MSI message from VTDIrq info */
> > +static void vtd_generate_msi_message(VTDIrq *irq, MSIMessage *msg_out)
> > +{
> > + VTD_MSIMessage msg = {};
> > +
> > + /* Generate address bits */
> > + msg.dest_mode = irq->dest_mode;
> > + msg.redir_hint = irq->redir_hint;
> > + msg.dest = irq->dest;
> > + msg.__addr_head = cpu_to_le32(0xfee);
> > + /* Keep this from original MSI address bits */
> > + msg.__not_used = irq->msi_addr_last_bits;
> > +
> > + /* Generate data bits */
> > + msg.vector = irq->vector;
> > + msg.delivery_mode = irq->delivery_mode;
> > + msg.level = 1;
> > + msg.trigger_mode = irq->trigger_mode;
> > +
> > + msg_out->address = msg.msi_addr;
> > + msg_out->data = msg.msi_data;
> > +}
> > +
> > +/* Interrupt remapping for MSI/MSI-X entry */
> > +static int vtd_interrupt_remap_msi(IntelIOMMUState *iommu,
> > + MSIMessage *origin,
> > + MSIMessage *translated)
> > +{
> > + int ret = 0;
> > + VTD_IR_MSIAddress addr;
> > + uint16_t index;
> > + VTDIrq irq = {0};
> > +
> > + assert(origin && translated);
> > +
> > + if (!iommu || !iommu->intr_enabled) {
> > + goto do_not_translate;
> > + }
> > +
> > + if (origin->address & VTD_MSI_ADDR_HI_MASK) {
> > + VTD_DPRINTF(GENERAL, "error: MSI addr high 32 bits nonzero"
> > + " during interrupt remapping: 0x%"PRIx32,
> > + (uint32_t)((origin->address & VTD_MSI_ADDR_HI_MASK) >>
> > \
> > + VTD_MSI_ADDR_HI_SHIFT));
> > + return -VTD_FR_IR_REQ_RSVD;
> > + }
> > +
> > + addr.data = origin->address & VTD_MSI_ADDR_LO_MASK;
>
> Below you treat data as LE, but here you use VTD_MSI_ADDR_LO_MASK
> which is native endian. This looks wrong to me.
You are right. I see that this is merged in master. Will fix this in
seperate patch.
Thanks,
-- peterx
