| Message ID | 20250207205613.474092-2-mjrosato@linux.ibm.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | s390x/pci: relax I/O address translation requirement | expand |
On Fri, 2025-02-07 at 15:56 -0500, Matthew Rosato wrote: > When receiving a guest mpcifc(4) or mpcifc(6) instruction without the T > bit set, treat this as a request to perform direct mapping instead of > address translation. In order to facilitate this, pin the entirety of > guest memory into the host iommu. > > Pinning for the direct mapping case is handled via vfio and its memory > listener. Additionally, ram discard settings are inherited from vfio: > coordinated discards (e.g. virtio-mem) are allowed while uncoordinated > discards (e.g. virtio-balloon) are disabled. > > Subsequent guest DMA operations are all expected to be of the format > guest_phys+sdma, allowing them to be used as lookup into the host > iommu table. > > Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com> > --- > hw/s390x/s390-pci-bus.c | 38 +++++++++++++++++++++++++++++++-- > hw/s390x/s390-pci-inst.c | 13 +++++++++-- > hw/s390x/s390-pci-vfio.c | 23 ++++++++++++++++---- > hw/s390x/s390-virtio-ccw.c | 5 +++++ > include/hw/s390x/s390-pci-bus.h | 4 ++++ > 5 files changed, 75 insertions(+), 8 deletions(-) > > ---8<--- > > static const VMStateDescription s390_pci_device_vmstate = { > diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c > index e386d75d58..8cdeb6cb7f 100644 > --- a/hw/s390x/s390-pci-inst.c > +++ b/hw/s390x/s390-pci-inst.c > @@ -16,6 +16,7 @@ > #include "exec/memory.h" > #include "qemu/error-report.h" > #include "system/hw_accel.h" > +#include "hw/boards.h" > #include "hw/pci/pci_device.h" > #include "hw/s390x/s390-pci-inst.h" > #include "hw/s390x/s390-pci-bus.h" > @@ -1008,17 +1009,25 @@ static int reg_ioat(CPUS390XState *env, S390PCIBusDevice *pbdev, ZpciFib fib, > } > > /* currently we only support designation type 1 with translation */ > - if (!(dt == ZPCI_IOTA_RTTO && t)) { > + if (t && dt != ZPCI_IOTA_RTTO) { > error_report("unsupported ioat dt %d t %d", dt, t); > s390_program_interrupt(env, PGM_OPERAND, ra); > return -EINVAL; > + } else if (!t && !pbdev->rtr_avail) { > + error_report("relaxed translation not allowed"); > + s390_program_interrupt(env, PGM_OPERAND, ra); > + return -EINVAL; > } > > iommu->pba = pba; > iommu->pal = pal; > iommu->g_iota = g_iota; > > - s390_pci_iommu_enable(iommu); > + if (t) { > + s390_pci_iommu_enable(iommu); > + } else { > + s390_pci_iommu_direct_map_enable(iommu); > + } > > return 0; > } > diff --git a/hw/s390x/s390-pci-vfio.c b/hw/s390x/s390-pci-vfio.c > index 7dbbc76823..443e222912 100644 > --- a/hw/s390x/s390-pci-vfio.c > +++ b/hw/s390x/s390-pci-vfio.c > @@ -131,13 +131,28 @@ static void s390_pci_read_base(S390PCIBusDevice *pbdev, > /* Store function type separately for type-specific behavior */ > pbdev->pft = cap->pft; > > + /* > + * If the device is a passthrough ISM device, disallow relaxed > + * translation. > + */ > + if (pbdev->pft == ZPCI_PFT_ISM) { > + pbdev->rtr_avail = false; > + } Just a note for external readers. The ISM device does work without the above but having explicit guest IOMMU mappings plus the respective shadow mappings in the host would catch driver misbehavior more easily. At the same time ISM uses long lived IOMMU mappings so the cost of shadowing its mappings is low. > + > /* > * If appropriate, reduce the size of the supported DMA aperture reported > - * to the guest based upon the vfio DMA limit. > + * to the guest based upon the vfio DMA limit. This is applicable for > + * devices that are guaranteed to not use relaxed translation. If the > + * device is capable of relaxed translation then we must advertise the > + * full aperture. In this case, if translation is used then we will > + * rely on the vfio DMA limit counting and use RPCIT CC1 / status 16 > + * to request that the guest free DMA mappings as necessary. > */ > - vfio_size = pbdev->iommu->max_dma_limit << TARGET_PAGE_BITS; > - if (vfio_size > 0 && vfio_size < cap->end_dma - cap->start_dma + 1) { > - pbdev->zpci_fn.edma = cap->start_dma + vfio_size - 1; > + if (!pbdev->rtr_avail) { > + vfio_size = pbdev->iommu->max_dma_limit << TARGET_PAGE_BITS; > + if (vfio_size > 0 && vfio_size < cap->end_dma - cap->start_dma + 1) { > + pbdev->zpci_fn.edma = cap->start_dma + vfio_size - 1; > + } > } > } > > diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c > index d9e683c5b4..6a6cb39808 100644 > --- a/hw/s390x/s390-virtio-ccw.c > +++ b/hw/s390x/s390-virtio-ccw.c > @@ -937,8 +937,13 @@ static void ccw_machine_9_2_instance_options(MachineState *machine) > > static void ccw_machine_9_2_class_options(MachineClass *mc) > { > + static GlobalProperty compat[] = { > + { TYPE_S390_PCI_DEVICE, "relaxed-translation", "off", }, > + }; > + > ccw_machine_10_0_class_options(mc); > compat_props_add(mc->compat_props, hw_compat_9_2, hw_compat_9_2_len); > + compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); > } > DEFINE_CCW_MACHINE(9, 2); > > diff --git a/include/hw/s390x/s390-pci-bus.h b/include/hw/s390x/s390-pci-bus.h > index 2c43ea123f..ea9e04ec49 100644 > --- a/include/hw/s390x/s390-pci-bus.h > +++ b/include/hw/s390x/s390-pci-bus.h > @@ -277,7 +277,9 @@ struct S390PCIIOMMU { > AddressSpace as; > MemoryRegion mr; > IOMMUMemoryRegion iommu_mr; > + MemoryRegion dm_mr; > bool enabled; > + bool direct_map; > uint64_t g_iota; > uint64_t pba; > uint64_t pal; > @@ -362,6 +364,7 @@ struct S390PCIBusDevice { > bool interp; > bool forwarding_assist; > bool aif; > + bool rtr_avail; > QTAILQ_ENTRY(S390PCIBusDevice) link; > }; > > @@ -389,6 +392,7 @@ int pci_chsc_sei_nt2_have_event(void); > void s390_pci_sclp_configure(SCCB *sccb); > void s390_pci_sclp_deconfigure(SCCB *sccb); > void s390_pci_iommu_enable(S390PCIIOMMU *iommu); > +void s390_pci_iommu_direct_map_enable(S390PCIIOMMU *iommu); > void s390_pci_iommu_disable(S390PCIIOMMU *iommu); > void s390_pci_generate_error_event(uint16_t pec, uint32_t fh, uint32_t fid, > uint64_t faddr, uint32_t e); I'm not too familiar with the existing code or QEMU in general, but the changes makes sense to me. I'm assuming the braces around single statement bodies are accepted style in QEMU? I retested this version together with the v4 of the kernel version too. So feel free to add: Tested-by: Niklas Schnelle <schnelle@linux.ibm.com> Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com>
On 2/10/25 14:12, Niklas Schnelle wrote: > On Fri, 2025-02-07 at 15:56 -0500, Matthew Rosato wrote: >> When receiving a guest mpcifc(4) or mpcifc(6) instruction without the T >> bit set, treat this as a request to perform direct mapping instead of >> address translation. In order to facilitate this, pin the entirety of >> guest memory into the host iommu. >> >> Pinning for the direct mapping case is handled via vfio and its memory >> listener. Additionally, ram discard settings are inherited from vfio: >> coordinated discards (e.g. virtio-mem) are allowed while uncoordinated >> discards (e.g. virtio-balloon) are disabled. >> >> Subsequent guest DMA operations are all expected to be of the format >> guest_phys+sdma, allowing them to be used as lookup into the host >> iommu table. >> >> Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com> >> --- >> hw/s390x/s390-pci-bus.c | 38 +++++++++++++++++++++++++++++++-- >> hw/s390x/s390-pci-inst.c | 13 +++++++++-- >> hw/s390x/s390-pci-vfio.c | 23 ++++++++++++++++---- >> hw/s390x/s390-virtio-ccw.c | 5 +++++ >> include/hw/s390x/s390-pci-bus.h | 4 ++++ >> 5 files changed, 75 insertions(+), 8 deletions(-) >> >> > ---8<--- >> >> static const VMStateDescription s390_pci_device_vmstate = { >> diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c >> index e386d75d58..8cdeb6cb7f 100644 >> --- a/hw/s390x/s390-pci-inst.c >> +++ b/hw/s390x/s390-pci-inst.c >> @@ -16,6 +16,7 @@ >> #include "exec/memory.h" >> #include "qemu/error-report.h" >> #include "system/hw_accel.h" >> +#include "hw/boards.h" >> #include "hw/pci/pci_device.h" >> #include "hw/s390x/s390-pci-inst.h" >> #include "hw/s390x/s390-pci-bus.h" >> @@ -1008,17 +1009,25 @@ static int reg_ioat(CPUS390XState *env, S390PCIBusDevice *pbdev, ZpciFib fib, >> } >> >> /* currently we only support designation type 1 with translation */ >> - if (!(dt == ZPCI_IOTA_RTTO && t)) { >> + if (t && dt != ZPCI_IOTA_RTTO) { >> error_report("unsupported ioat dt %d t %d", dt, t); >> s390_program_interrupt(env, PGM_OPERAND, ra); >> return -EINVAL; >> + } else if (!t && !pbdev->rtr_avail) { >> + error_report("relaxed translation not allowed"); >> + s390_program_interrupt(env, PGM_OPERAND, ra); >> + return -EINVAL; >> } >> >> iommu->pba = pba; >> iommu->pal = pal; >> iommu->g_iota = g_iota; >> >> - s390_pci_iommu_enable(iommu); >> + if (t) { >> + s390_pci_iommu_enable(iommu); >> + } else { >> + s390_pci_iommu_direct_map_enable(iommu); >> + } >> >> return 0; >> } >> diff --git a/hw/s390x/s390-pci-vfio.c b/hw/s390x/s390-pci-vfio.c >> index 7dbbc76823..443e222912 100644 >> --- a/hw/s390x/s390-pci-vfio.c >> +++ b/hw/s390x/s390-pci-vfio.c >> @@ -131,13 +131,28 @@ static void s390_pci_read_base(S390PCIBusDevice *pbdev, >> /* Store function type separately for type-specific behavior */ >> pbdev->pft = cap->pft; >> >> + /* >> + * If the device is a passthrough ISM device, disallow relaxed >> + * translation. >> + */ >> + if (pbdev->pft == ZPCI_PFT_ISM) { >> + pbdev->rtr_avail = false; >> + } > > Just a note for external readers. The ISM device does work without the > above but having explicit guest IOMMU mappings plus the respective > shadow mappings in the host would catch driver misbehavior more easily. > At the same time ISM uses long lived IOMMU mappings so the cost of > shadowing its mappings is low. > >> + >> /* >> * If appropriate, reduce the size of the supported DMA aperture reported >> - * to the guest based upon the vfio DMA limit. >> + * to the guest based upon the vfio DMA limit. This is applicable for >> + * devices that are guaranteed to not use relaxed translation. If the >> + * device is capable of relaxed translation then we must advertise the >> + * full aperture. In this case, if translation is used then we will >> + * rely on the vfio DMA limit counting and use RPCIT CC1 / status 16 >> + * to request that the guest free DMA mappings as necessary. >> */ >> - vfio_size = pbdev->iommu->max_dma_limit << TARGET_PAGE_BITS; >> - if (vfio_size > 0 && vfio_size < cap->end_dma - cap->start_dma + 1) { >> - pbdev->zpci_fn.edma = cap->start_dma + vfio_size - 1; >> + if (!pbdev->rtr_avail) { >> + vfio_size = pbdev->iommu->max_dma_limit << TARGET_PAGE_BITS; >> + if (vfio_size > 0 && vfio_size < cap->end_dma - cap->start_dma + 1) { >> + pbdev->zpci_fn.edma = cap->start_dma + vfio_size - 1; >> + } >> } >> } >> >> diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c >> index d9e683c5b4..6a6cb39808 100644 >> --- a/hw/s390x/s390-virtio-ccw.c >> +++ b/hw/s390x/s390-virtio-ccw.c >> @@ -937,8 +937,13 @@ static void ccw_machine_9_2_instance_options(MachineState *machine) >> >> static void ccw_machine_9_2_class_options(MachineClass *mc) >> { >> + static GlobalProperty compat[] = { >> + { TYPE_S390_PCI_DEVICE, "relaxed-translation", "off", }, >> + }; >> + >> ccw_machine_10_0_class_options(mc); >> compat_props_add(mc->compat_props, hw_compat_9_2, hw_compat_9_2_len); >> + compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); >> } >> DEFINE_CCW_MACHINE(9, 2); >> >> diff --git a/include/hw/s390x/s390-pci-bus.h b/include/hw/s390x/s390-pci-bus.h >> index 2c43ea123f..ea9e04ec49 100644 >> --- a/include/hw/s390x/s390-pci-bus.h >> +++ b/include/hw/s390x/s390-pci-bus.h >> @@ -277,7 +277,9 @@ struct S390PCIIOMMU { >> AddressSpace as; >> MemoryRegion mr; >> IOMMUMemoryRegion iommu_mr; >> + MemoryRegion dm_mr; >> bool enabled; >> + bool direct_map; >> uint64_t g_iota; >> uint64_t pba; >> uint64_t pal; >> @@ -362,6 +364,7 @@ struct S390PCIBusDevice { >> bool interp; >> bool forwarding_assist; >> bool aif; >> + bool rtr_avail; >> QTAILQ_ENTRY(S390PCIBusDevice) link; >> }; >> >> @@ -389,6 +392,7 @@ int pci_chsc_sei_nt2_have_event(void); >> void s390_pci_sclp_configure(SCCB *sccb); >> void s390_pci_sclp_deconfigure(SCCB *sccb); >> void s390_pci_iommu_enable(S390PCIIOMMU *iommu); >> +void s390_pci_iommu_direct_map_enable(S390PCIIOMMU *iommu); >> void s390_pci_iommu_disable(S390PCIIOMMU *iommu); >> void s390_pci_generate_error_event(uint16_t pec, uint32_t fh, uint32_t fid, >> uint64_t faddr, uint32_t e); > > I'm not too familiar with the existing code or QEMU in general, but the > changes makes sense to me. I'm assuming the braces around single > statement bodies are accepted style in QEMU? They are required : https://qemu.readthedocs.io/en/v9.2.0/devel/style.html#block-structure > > I retested this version together with the v4 of the kernel version too. > So feel free to add: > > Tested-by: Niklas Schnelle <schnelle@linux.ibm.com> > Reviewed-by: Niklas Schnelle <schnelle@linux.ibm.com> > Thanks, C.
On 07.02.25 21:56, Matthew Rosato wrote: > When receiving a guest mpcifc(4) or mpcifc(6) instruction without the T > bit set, treat this as a request to perform direct mapping instead of > address translation. In order to facilitate this, pin the entirety of > guest memory into the host iommu. > > Pinning for the direct mapping case is handled via vfio and its memory > listener. Additionally, ram discard settings are inherited from vfio: > coordinated discards (e.g. virtio-mem) are allowed while uncoordinated > discards (e.g. virtio-balloon) are disabled. > > Subsequent guest DMA operations are all expected to be of the format > guest_phys+sdma, allowing them to be used as lookup into the host > iommu table. > > Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com> > --- > hw/s390x/s390-pci-bus.c | 38 +++++++++++++++++++++++++++++++-- > hw/s390x/s390-pci-inst.c | 13 +++++++++-- > hw/s390x/s390-pci-vfio.c | 23 ++++++++++++++++---- > hw/s390x/s390-virtio-ccw.c | 5 +++++ > include/hw/s390x/s390-pci-bus.h | 4 ++++ > 5 files changed, 75 insertions(+), 8 deletions(-) > > diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c > index eead269cc2..81e5843c81 100644 > --- a/hw/s390x/s390-pci-bus.c > +++ b/hw/s390x/s390-pci-bus.c > @@ -18,6 +18,8 @@ > #include "hw/s390x/s390-pci-inst.h" > #include "hw/s390x/s390-pci-kvm.h" > #include "hw/s390x/s390-pci-vfio.h" > +#include "hw/s390x/s390-virtio-ccw.h" > +#include "hw/boards.h" > #include "hw/pci/pci_bus.h" > #include "hw/qdev-properties.h" > #include "hw/pci/pci_bridge.h" > @@ -720,16 +722,45 @@ void s390_pci_iommu_enable(S390PCIIOMMU *iommu) > TYPE_S390_IOMMU_MEMORY_REGION, OBJECT(&iommu->mr), > name, iommu->pal + 1); > iommu->enabled = true; > + iommu->direct_map = false; > memory_region_add_subregion(&iommu->mr, 0, MEMORY_REGION(&iommu->iommu_mr)); > g_free(name); > } > > +void s390_pci_iommu_direct_map_enable(S390PCIIOMMU *iommu) > +{ > + MachineState *ms = MACHINE(qdev_get_machine()); > + S390CcwMachineState *s390ms = S390_CCW_MACHINE(ms); > + > + /* > + * For direct-mapping we must map the entire guest address space. Rather > + * than using an iommu, create a memory region alias that maps GPA X to > + * IOVA X + SDMA. VFIO will handle pinning via its memory listener. > + */ > + g_autofree char *name = g_strdup_printf("iommu-dm-s390-%04x", > + iommu->pbdev->uid); Empty line. > + memory_region_init_alias(&iommu->dm_mr, OBJECT(&iommu->mr), name, > + get_system_memory(), 0, > + s390_get_memory_limit(s390ms)); > + iommu->enabled = true; > + iommu->direct_map = true; You could dynamically allocate the dm_mr instead, and use that as indication if the direct mapping is active. Whatever you prefer. Nothing else jumped at me, thanks!
diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c index eead269cc2..81e5843c81 100644 --- a/hw/s390x/s390-pci-bus.c +++ b/hw/s390x/s390-pci-bus.c @@ -18,6 +18,8 @@ #include "hw/s390x/s390-pci-inst.h" #include "hw/s390x/s390-pci-kvm.h" #include "hw/s390x/s390-pci-vfio.h" +#include "hw/s390x/s390-virtio-ccw.h" +#include "hw/boards.h" #include "hw/pci/pci_bus.h" #include "hw/qdev-properties.h" #include "hw/pci/pci_bridge.h" @@ -720,16 +722,45 @@ void s390_pci_iommu_enable(S390PCIIOMMU *iommu) TYPE_S390_IOMMU_MEMORY_REGION, OBJECT(&iommu->mr), name, iommu->pal + 1); iommu->enabled = true; + iommu->direct_map = false; memory_region_add_subregion(&iommu->mr, 0, MEMORY_REGION(&iommu->iommu_mr)); g_free(name); } +void s390_pci_iommu_direct_map_enable(S390PCIIOMMU *iommu) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + S390CcwMachineState *s390ms = S390_CCW_MACHINE(ms); + + /* + * For direct-mapping we must map the entire guest address space. Rather + * than using an iommu, create a memory region alias that maps GPA X to + * IOVA X + SDMA. VFIO will handle pinning via its memory listener. + */ + g_autofree char *name = g_strdup_printf("iommu-dm-s390-%04x", + iommu->pbdev->uid); + memory_region_init_alias(&iommu->dm_mr, OBJECT(&iommu->mr), name, + get_system_memory(), 0, + s390_get_memory_limit(s390ms)); + iommu->enabled = true; + iommu->direct_map = true; + memory_region_add_subregion(&iommu->mr, iommu->pbdev->zpci_fn.sdma, + &iommu->dm_mr); +} + void s390_pci_iommu_disable(S390PCIIOMMU *iommu) { iommu->enabled = false; g_hash_table_remove_all(iommu->iotlb); - memory_region_del_subregion(&iommu->mr, MEMORY_REGION(&iommu->iommu_mr)); - object_unparent(OBJECT(&iommu->iommu_mr)); + if (iommu->direct_map) { + memory_region_del_subregion(&iommu->mr, &iommu->dm_mr); + iommu->direct_map = false; + object_unparent(OBJECT(&iommu->dm_mr)); + } else { + memory_region_del_subregion(&iommu->mr, + MEMORY_REGION(&iommu->iommu_mr)); + object_unparent(OBJECT(&iommu->iommu_mr)); + } } static void s390_pci_iommu_free(S390pciState *s, PCIBus *bus, int32_t devfn) @@ -1130,6 +1161,7 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, /* Always intercept emulated devices */ pbdev->interp = false; pbdev->forwarding_assist = false; + pbdev->rtr_avail = false; } if (s390_pci_msix_init(pbdev) && !pbdev->interp) { @@ -1488,6 +1520,8 @@ static const Property s390_pci_device_properties[] = { DEFINE_PROP_BOOL("interpret", S390PCIBusDevice, interp, true), DEFINE_PROP_BOOL("forwarding-assist", S390PCIBusDevice, forwarding_assist, true), + DEFINE_PROP_BOOL("relaxed-translation", S390PCIBusDevice, rtr_avail, + true), }; static const VMStateDescription s390_pci_device_vmstate = { diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c index e386d75d58..8cdeb6cb7f 100644 --- a/hw/s390x/s390-pci-inst.c +++ b/hw/s390x/s390-pci-inst.c @@ -16,6 +16,7 @@ #include "exec/memory.h" #include "qemu/error-report.h" #include "system/hw_accel.h" +#include "hw/boards.h" #include "hw/pci/pci_device.h" #include "hw/s390x/s390-pci-inst.h" #include "hw/s390x/s390-pci-bus.h" @@ -1008,17 +1009,25 @@ static int reg_ioat(CPUS390XState *env, S390PCIBusDevice *pbdev, ZpciFib fib, } /* currently we only support designation type 1 with translation */ - if (!(dt == ZPCI_IOTA_RTTO && t)) { + if (t && dt != ZPCI_IOTA_RTTO) { error_report("unsupported ioat dt %d t %d", dt, t); s390_program_interrupt(env, PGM_OPERAND, ra); return -EINVAL; + } else if (!t && !pbdev->rtr_avail) { + error_report("relaxed translation not allowed"); + s390_program_interrupt(env, PGM_OPERAND, ra); + return -EINVAL; } iommu->pba = pba; iommu->pal = pal; iommu->g_iota = g_iota; - s390_pci_iommu_enable(iommu); + if (t) { + s390_pci_iommu_enable(iommu); + } else { + s390_pci_iommu_direct_map_enable(iommu); + } return 0; } diff --git a/hw/s390x/s390-pci-vfio.c b/hw/s390x/s390-pci-vfio.c index 7dbbc76823..443e222912 100644 --- a/hw/s390x/s390-pci-vfio.c +++ b/hw/s390x/s390-pci-vfio.c @@ -131,13 +131,28 @@ static void s390_pci_read_base(S390PCIBusDevice *pbdev, /* Store function type separately for type-specific behavior */ pbdev->pft = cap->pft; + /* + * If the device is a passthrough ISM device, disallow relaxed + * translation. + */ + if (pbdev->pft == ZPCI_PFT_ISM) { + pbdev->rtr_avail = false; + } + /* * If appropriate, reduce the size of the supported DMA aperture reported - * to the guest based upon the vfio DMA limit. + * to the guest based upon the vfio DMA limit. This is applicable for + * devices that are guaranteed to not use relaxed translation. If the + * device is capable of relaxed translation then we must advertise the + * full aperture. In this case, if translation is used then we will + * rely on the vfio DMA limit counting and use RPCIT CC1 / status 16 + * to request that the guest free DMA mappings as necessary. */ - vfio_size = pbdev->iommu->max_dma_limit << TARGET_PAGE_BITS; - if (vfio_size > 0 && vfio_size < cap->end_dma - cap->start_dma + 1) { - pbdev->zpci_fn.edma = cap->start_dma + vfio_size - 1; + if (!pbdev->rtr_avail) { + vfio_size = pbdev->iommu->max_dma_limit << TARGET_PAGE_BITS; + if (vfio_size > 0 && vfio_size < cap->end_dma - cap->start_dma + 1) { + pbdev->zpci_fn.edma = cap->start_dma + vfio_size - 1; + } } } diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index d9e683c5b4..6a6cb39808 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -937,8 +937,13 @@ static void ccw_machine_9_2_instance_options(MachineState *machine) static void ccw_machine_9_2_class_options(MachineClass *mc) { + static GlobalProperty compat[] = { + { TYPE_S390_PCI_DEVICE, "relaxed-translation", "off", }, + }; + ccw_machine_10_0_class_options(mc); compat_props_add(mc->compat_props, hw_compat_9_2, hw_compat_9_2_len); + compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); } DEFINE_CCW_MACHINE(9, 2); diff --git a/include/hw/s390x/s390-pci-bus.h b/include/hw/s390x/s390-pci-bus.h index 2c43ea123f..ea9e04ec49 100644 --- a/include/hw/s390x/s390-pci-bus.h +++ b/include/hw/s390x/s390-pci-bus.h @@ -277,7 +277,9 @@ struct S390PCIIOMMU { AddressSpace as; MemoryRegion mr; IOMMUMemoryRegion iommu_mr; + MemoryRegion dm_mr; bool enabled; + bool direct_map; uint64_t g_iota; uint64_t pba; uint64_t pal; @@ -362,6 +364,7 @@ struct S390PCIBusDevice { bool interp; bool forwarding_assist; bool aif; + bool rtr_avail; QTAILQ_ENTRY(S390PCIBusDevice) link; }; @@ -389,6 +392,7 @@ int pci_chsc_sei_nt2_have_event(void); void s390_pci_sclp_configure(SCCB *sccb); void s390_pci_sclp_deconfigure(SCCB *sccb); void s390_pci_iommu_enable(S390PCIIOMMU *iommu); +void s390_pci_iommu_direct_map_enable(S390PCIIOMMU *iommu); void s390_pci_iommu_disable(S390PCIIOMMU *iommu); void s390_pci_generate_error_event(uint16_t pec, uint32_t fh, uint32_t fid, uint64_t faddr, uint32_t e);
When receiving a guest mpcifc(4) or mpcifc(6) instruction without the T bit set, treat this as a request to perform direct mapping instead of address translation. In order to facilitate this, pin the entirety of guest memory into the host iommu. Pinning for the direct mapping case is handled via vfio and its memory listener. Additionally, ram discard settings are inherited from vfio: coordinated discards (e.g. virtio-mem) are allowed while uncoordinated discards (e.g. virtio-balloon) are disabled. Subsequent guest DMA operations are all expected to be of the format guest_phys+sdma, allowing them to be used as lookup into the host iommu table. Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com> --- hw/s390x/s390-pci-bus.c | 38 +++++++++++++++++++++++++++++++-- hw/s390x/s390-pci-inst.c | 13 +++++++++-- hw/s390x/s390-pci-vfio.c | 23 ++++++++++++++++---- hw/s390x/s390-virtio-ccw.c | 5 +++++ include/hw/s390x/s390-pci-bus.h | 4 ++++ 5 files changed, 75 insertions(+), 8 deletions(-)