diff options
author | Singh, Brijesh <brijesh.singh@amd.com> | 2018-10-01 19:44:39 +0000 |
---|---|---|
committer | Michael S. Tsirkin <mst@redhat.com> | 2018-11-05 13:24:02 -0500 |
commit | b44159fe00784f67f766ba1bf6eec14f3c709806 (patch) | |
tree | 5bcbfefd1278e90352346ae46e8b8d28aa3ad45c | |
parent | 577c470f4326eae22e4e412946b167075f4440d2 (diff) |
x86_iommu/amd: Add interrupt remap support when VAPIC is not enabled
Emulate the interrupt remapping support when guest virtual APIC is
not enabled.
For more info Refer: AMD IOMMU spec Rev 3.0 - section 2.2.5.1
When VAPIC is not enabled, it uses interrupt remapping as defined in
Table 20 and Figure 15 from IOMMU spec.
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Cc: Tom Lendacky <Thomas.Lendacky@amd.com>
Cc: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
-rw-r--r-- | hw/i386/amd_iommu.c | 199 | ||||
-rw-r--r-- | hw/i386/amd_iommu.h | 46 | ||||
-rw-r--r-- | hw/i386/trace-events | 7 |
3 files changed, 250 insertions, 2 deletions
diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c index 9118a75530..8e2f13c029 100644 --- a/hw/i386/amd_iommu.c +++ b/hw/i386/amd_iommu.c @@ -28,6 +28,7 @@ #include "qemu/error-report.h" #include "hw/i386/apic_internal.h" #include "trace.h" +#include "hw/i386/apic-msidef.h" /* used AMD-Vi MMIO registers */ const char *amdvi_mmio_low[] = { @@ -1032,21 +1033,146 @@ static IOMMUTLBEntry amdvi_translate(IOMMUMemoryRegion *iommu, hwaddr addr, return ret; } +static int amdvi_get_irte(AMDVIState *s, MSIMessage *origin, uint64_t *dte, + union irte *irte, uint16_t devid) +{ + uint64_t irte_root, offset; + + irte_root = dte[2] & AMDVI_IR_PHYS_ADDR_MASK; + offset = (origin->data & AMDVI_IRTE_OFFSET) << 2; + + trace_amdvi_ir_irte(irte_root, offset); + + if (dma_memory_read(&address_space_memory, irte_root + offset, + irte, sizeof(*irte))) { + trace_amdvi_ir_err("failed to get irte"); + return -AMDVI_IR_GET_IRTE; + } + + trace_amdvi_ir_irte_val(irte->val); + + return 0; +} + +static int amdvi_int_remap_legacy(AMDVIState *iommu, + MSIMessage *origin, + MSIMessage *translated, + uint64_t *dte, + X86IOMMUIrq *irq, + uint16_t sid) +{ + int ret; + union irte irte; + + /* get interrupt remapping table */ + ret = amdvi_get_irte(iommu, origin, dte, &irte, sid); + if (ret < 0) { + return ret; + } + + if (!irte.fields.valid) { + trace_amdvi_ir_target_abort("RemapEn is disabled"); + return -AMDVI_IR_TARGET_ABORT; + } + + if (irte.fields.guest_mode) { + error_report_once("guest mode is not zero"); + return -AMDVI_IR_ERR; + } + + if (irte.fields.int_type > AMDVI_IOAPIC_INT_TYPE_ARBITRATED) { + error_report_once("reserved int_type"); + return -AMDVI_IR_ERR; + } + + irq->delivery_mode = irte.fields.int_type; + irq->vector = irte.fields.vector; + irq->dest_mode = irte.fields.dm; + irq->redir_hint = irte.fields.rq_eoi; + irq->dest = irte.fields.destination; + + return 0; +} + +static int __amdvi_int_remap_msi(AMDVIState *iommu, + MSIMessage *origin, + MSIMessage *translated, + uint64_t *dte, + X86IOMMUIrq *irq, + uint16_t sid) +{ + uint8_t int_ctl; + + int_ctl = (dte[2] >> AMDVI_IR_INTCTL_SHIFT) & 3; + trace_amdvi_ir_intctl(int_ctl); + + switch (int_ctl) { + case AMDVI_IR_INTCTL_PASS: + memcpy(translated, origin, sizeof(*origin)); + return 0; + case AMDVI_IR_INTCTL_REMAP: + break; + case AMDVI_IR_INTCTL_ABORT: + trace_amdvi_ir_target_abort("int_ctl abort"); + return -AMDVI_IR_TARGET_ABORT; + default: + trace_amdvi_ir_err("int_ctl reserved"); + return -AMDVI_IR_ERR; + } + + return amdvi_int_remap_legacy(iommu, origin, translated, dte, irq, sid); +} + /* Interrupt remapping for MSI/MSI-X entry */ static int amdvi_int_remap_msi(AMDVIState *iommu, MSIMessage *origin, MSIMessage *translated, uint16_t sid) { + int ret = 0; + uint64_t pass = 0; + uint64_t dte[4] = { 0 }; + X86IOMMUIrq irq = { 0 }; + uint8_t dest_mode, delivery_mode; + assert(origin && translated); + /* + * When IOMMU is enabled, interrupt remap request will come either from + * IO-APIC or PCI device. If interrupt is from PCI device then it will + * have a valid requester id but if the interrupt is from IO-APIC + * then requester id will be invalid. + */ + if (sid == X86_IOMMU_SID_INVALID) { + sid = AMDVI_IOAPIC_SB_DEVID; + } + trace_amdvi_ir_remap_msi_req(origin->address, origin->data, sid); - if (!iommu || !X86_IOMMU_DEVICE(iommu)->intr_supported) { + /* check if device table entry is set before we go further. */ + if (!iommu || !iommu->devtab_len) { memcpy(translated, origin, sizeof(*origin)); goto out; } + if (!amdvi_get_dte(iommu, sid, dte)) { + return -AMDVI_IR_ERR; + } + + /* Check if IR is enabled in DTE */ + if (!(dte[2] & AMDVI_IR_REMAP_ENABLE)) { + memcpy(translated, origin, sizeof(*origin)); + goto out; + } + + /* validate that we are configure with intremap=on */ + if (!X86_IOMMU_DEVICE(iommu)->intr_supported) { + trace_amdvi_err("Interrupt remapping is enabled in the guest but " + "not in the host. Use intremap=on to enable interrupt " + "remapping in amd-iommu."); + return -AMDVI_IR_ERR; + } + if (origin->address & AMDVI_MSI_ADDR_HI_MASK) { trace_amdvi_err("MSI address high 32 bits non-zero when " "Interrupt Remapping enabled."); @@ -1058,10 +1184,81 @@ static int amdvi_int_remap_msi(AMDVIState *iommu, return -AMDVI_IR_ERR; } + /* + * The MSI data register [10:8] are used to get the upstream interrupt type. + * + * See MSI/MSI-X format: + * https://pdfs.semanticscholar.org/presentation/9420/c279e942eca568157711ef5c92b800c40a79.pdf + * (page 5) + */ + delivery_mode = (origin->data >> MSI_DATA_DELIVERY_MODE_SHIFT) & 7; + + switch (delivery_mode) { + case AMDVI_IOAPIC_INT_TYPE_FIXED: + case AMDVI_IOAPIC_INT_TYPE_ARBITRATED: + trace_amdvi_ir_delivery_mode("fixed/arbitrated"); + ret = __amdvi_int_remap_msi(iommu, origin, translated, dte, &irq, sid); + if (ret < 0) { + goto remap_fail; + } else { + /* Translate IRQ to MSI messages */ + x86_iommu_irq_to_msi_message(&irq, translated); + goto out; + } + break; + case AMDVI_IOAPIC_INT_TYPE_SMI: + error_report("SMI is not supported!"); + ret = -AMDVI_IR_ERR; + break; + case AMDVI_IOAPIC_INT_TYPE_NMI: + pass = dte[3] & AMDVI_DEV_NMI_PASS_MASK; + trace_amdvi_ir_delivery_mode("nmi"); + break; + case AMDVI_IOAPIC_INT_TYPE_INIT: + pass = dte[3] & AMDVI_DEV_INT_PASS_MASK; + trace_amdvi_ir_delivery_mode("init"); + break; + case AMDVI_IOAPIC_INT_TYPE_EINT: + pass = dte[3] & AMDVI_DEV_EINT_PASS_MASK; + trace_amdvi_ir_delivery_mode("eint"); + break; + default: + trace_amdvi_ir_delivery_mode("unsupported delivery_mode"); + ret = -AMDVI_IR_ERR; + break; + } + + if (ret < 0) { + goto remap_fail; + } + + /* + * The MSI address register bit[2] is used to get the destination + * mode. The dest_mode 1 is valid for fixed and arbitrated interrupts + * only. + */ + dest_mode = (origin->address >> MSI_ADDR_DEST_MODE_SHIFT) & 1; + if (dest_mode) { + trace_amdvi_ir_err("invalid dest_mode"); + ret = -AMDVI_IR_ERR; + goto remap_fail; + } + + if (pass) { + memcpy(translated, origin, sizeof(*origin)); + } else { + trace_amdvi_ir_err("passthrough is not enabled"); + ret = -AMDVI_IR_ERR; + goto remap_fail; + } + out: trace_amdvi_ir_remap_msi(origin->address, origin->data, translated->address, translated->data); return 0; + +remap_fail: + return ret; } static int amdvi_int_remap(X86IOMMUState *iommu, diff --git a/hw/i386/amd_iommu.h b/hw/i386/amd_iommu.h index 4e7cc271c4..f73be48fca 100644 --- a/hw/i386/amd_iommu.h +++ b/hw/i386/amd_iommu.h @@ -217,7 +217,51 @@ /* Interrupt remapping errors */ #define AMDVI_IR_ERR 0x1 - +#define AMDVI_IR_GET_IRTE 0x2 +#define AMDVI_IR_TARGET_ABORT 0x3 + +/* Interrupt remapping */ +#define AMDVI_IR_REMAP_ENABLE 1ULL +#define AMDVI_IR_INTCTL_SHIFT 60 +#define AMDVI_IR_INTCTL_ABORT 0 +#define AMDVI_IR_INTCTL_PASS 1 +#define AMDVI_IR_INTCTL_REMAP 2 + +#define AMDVI_IR_PHYS_ADDR_MASK (((1ULL << 45) - 1) << 6) + +/* MSI data 10:0 bits (section 2.2.5.1 Fig 14) */ +#define AMDVI_IRTE_OFFSET 0x7ff + +/* Delivery mode of MSI data (same as IOAPIC deilver mode encoding) */ +#define AMDVI_IOAPIC_INT_TYPE_FIXED 0x0 +#define AMDVI_IOAPIC_INT_TYPE_ARBITRATED 0x1 +#define AMDVI_IOAPIC_INT_TYPE_SMI 0x2 +#define AMDVI_IOAPIC_INT_TYPE_NMI 0x4 +#define AMDVI_IOAPIC_INT_TYPE_INIT 0x5 +#define AMDVI_IOAPIC_INT_TYPE_EINT 0x7 + +/* Pass through interrupt */ +#define AMDVI_DEV_INT_PASS_MASK (1UL << 56) +#define AMDVI_DEV_EINT_PASS_MASK (1UL << 57) +#define AMDVI_DEV_NMI_PASS_MASK (1UL << 58) +#define AMDVI_DEV_LINT0_PASS_MASK (1UL << 62) +#define AMDVI_DEV_LINT1_PASS_MASK (1UL << 63) + +/* Interrupt remapping table fields (Guest VAPIC not enabled) */ +union irte { + uint32_t val; + struct { + uint32_t valid:1, + no_fault:1, + int_type:3, + rq_eoi:1, + dm:1, + guest_mode:1, + destination:8, + vector:8, + rsvd:8; + } fields; +}; #define TYPE_AMD_IOMMU_DEVICE "amd-iommu" #define AMD_IOMMU_DEVICE(obj)\ diff --git a/hw/i386/trace-events b/hw/i386/trace-events index 41d533c250..98150c93db 100644 --- a/hw/i386/trace-events +++ b/hw/i386/trace-events @@ -106,6 +106,13 @@ amdvi_mem_ir_write(uint64_t addr, uint64_t val) "addr 0x%"PRIx64" data 0x%"PRIx6 amdvi_ir_remap_msi_req(uint64_t addr, uint64_t data, uint8_t devid) "addr 0x%"PRIx64" data 0x%"PRIx64" devid 0x%"PRIx8 amdvi_ir_remap_msi(uint64_t addr, uint64_t data, uint64_t addr2, uint64_t data2) "(addr 0x%"PRIx64", data 0x%"PRIx64") -> (addr 0x%"PRIx64", data 0x%"PRIx64")" amdvi_err(const char *str) "%s" +amdvi_ir_irte(uint64_t addr, uint64_t data) "addr 0x%"PRIx64" offset 0x%"PRIx64 +amdvi_ir_irte_val(uint32_t data) "data 0x%"PRIx32 +amdvi_ir_err(const char *str) "%s" +amdvi_ir_intctl(uint8_t val) "int_ctl 0x%"PRIx8 +amdvi_ir_target_abort(const char *str) "%s" +amdvi_ir_delivery_mode(const char *str) "%s" +amdvi_ir_generate_msi_message(uint8_t vector, uint8_t delivery_mode, uint8_t dest_mode, uint8_t dest, uint8_t rh) "vector %d delivery-mode %d dest-mode %d dest-id %d rh %d" # hw/i386/vmport.c vmport_register(unsigned char command, void *func, void *opaque) "command: 0x%02x func: %p opaque: %p" |