diff options
Diffstat (limited to 'hw/pci')
| -rw-r--r-- | hw/pci/msix.c | 2 | ||||
| -rw-r--r-- | hw/pci/pci.c | 287 | ||||
| -rw-r--r-- | hw/pci/pci_host.c | 6 | ||||
| -rw-r--r-- | hw/pci/pcie.c | 78 | ||||
| -rw-r--r-- | hw/pci/pcie_sriov.c | 336 |
5 files changed, 594 insertions, 115 deletions
diff --git a/hw/pci/msix.c b/hw/pci/msix.c index 66f27b9..8c7f670 100644 --- a/hw/pci/msix.c +++ b/hw/pci/msix.c @@ -72,7 +72,7 @@ static uint8_t *msix_pending_byte(PCIDevice *dev, int vector) return dev->msix_pba + vector / 8; } -static int msix_is_pending(PCIDevice *dev, int vector) +int msix_is_pending(PCIDevice *dev, unsigned int vector) { return *msix_pending_byte(dev, vector) & msix_pending_mask(vector); } diff --git a/hw/pci/pci.c b/hw/pci/pci.c index 352b3d1..c70b5ce 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -32,6 +32,7 @@ #include "hw/pci/pci_host.h" #include "hw/qdev-properties.h" #include "hw/qdev-properties-system.h" +#include "migration/cpr.h" #include "migration/qemu-file-types.h" #include "migration/vmstate.h" #include "net/net.h" @@ -94,6 +95,7 @@ static const Property pci_props[] = { QEMU_PCIE_ARI_NEXTFN_1_BITNR, false), DEFINE_PROP_SIZE32("x-max-bounce-buffer-size", PCIDevice, max_bounce_buffer_size, DEFAULT_MAX_BOUNCE_BUFFER_SIZE), + DEFINE_PROP_STRING("sriov-pf", PCIDevice, sriov_pf), DEFINE_PROP_BIT("x-pcie-ext-tag", PCIDevice, cap_present, QEMU_PCIE_EXT_TAG_BITNR, true), { .name = "busnr", .info = &prop_pci_busnr }, @@ -127,6 +129,12 @@ static GSequence *pci_acpi_index_list(void) return used_acpi_index_list; } +static void pci_set_master(PCIDevice *d, bool enable) +{ + memory_region_set_enabled(&d->bus_master_enable_region, enable); + d->is_master = enable; /* cache the status */ +} + static void pci_init_bus_master(PCIDevice *pci_dev) { AddressSpace *dma_as = pci_device_iommu_address_space(pci_dev); @@ -134,7 +142,7 @@ static void pci_init_bus_master(PCIDevice *pci_dev) memory_region_init_alias(&pci_dev->bus_master_enable_region, OBJECT(pci_dev), "bus master", dma_as->root, 0, memory_region_size(dma_as->root)); - memory_region_set_enabled(&pci_dev->bus_master_enable_region, false); + pci_set_master(pci_dev, false); memory_region_add_subregion(&pci_dev->bus_master_container_region, 0, &pci_dev->bus_master_enable_region); } @@ -530,6 +538,10 @@ static void pci_reset_regions(PCIDevice *dev) static void pci_do_device_reset(PCIDevice *dev) { + if ((dev->cap_present & QEMU_PCI_SKIP_RESET_ON_CPR) && cpr_is_incoming()) { + return; + } + pci_device_deassert_intx(dev); assert(dev->irq_state == 0); @@ -803,9 +815,8 @@ static int get_pci_config_device(QEMUFile *f, void *pv, size_t size, pci_bridge_update_mappings(PCI_BRIDGE(s)); } - memory_region_set_enabled(&s->bus_master_enable_region, - pci_get_word(s->config + PCI_COMMAND) - & PCI_COMMAND_MASTER); + pci_set_master(s, pci_get_word(s->config + PCI_COMMAND) + & PCI_COMMAND_MASTER); g_free(config); return 0; @@ -1105,13 +1116,8 @@ static void pci_init_multifunction(PCIBus *bus, PCIDevice *dev, Error **errp) dev->config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION; } - /* - * With SR/IOV and ARI, a device at function 0 need not be a multifunction - * device, as it may just be a VF that ended up with function 0 in - * the legacy PCI interpretation. Avoid failing in such cases: - */ - if (pci_is_vf(dev) && - dev->exp.sriov_vf.pf->cap_present & QEMU_PCI_CAP_MULTIFUNCTION) { + /* SR/IOV is not handled here. */ + if (pci_is_vf(dev)) { return; } @@ -1144,7 +1150,8 @@ static void pci_init_multifunction(PCIBus *bus, PCIDevice *dev, Error **errp) } /* function 0 indicates single function, so function > 0 must be NULL */ for (func = 1; func < PCI_FUNC_MAX; ++func) { - if (bus->devices[PCI_DEVFN(slot, func)]) { + PCIDevice *device = bus->devices[PCI_DEVFN(slot, func)]; + if (device && !pci_is_vf(device)) { error_setg(errp, "PCI: %x.0 indicates single function, " "but %x.%x is already populated.", slot, slot, func); @@ -1432,6 +1439,7 @@ static void pci_qdev_unrealize(DeviceState *dev) pci_unregister_io_regions(pci_dev); pci_del_option_rom(pci_dev); + pcie_sriov_unregister_device(pci_dev); if (pc->exit) { pc->exit(pci_dev); @@ -1463,7 +1471,6 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num, pcibus_t size = memory_region_size(memory); uint8_t hdr_type; - assert(!pci_is_vf(pci_dev)); /* VFs must use pcie_sriov_vf_register_bar */ assert(region_num >= 0); assert(region_num < PCI_NUM_REGIONS); assert(is_power_of_2(size)); @@ -1475,7 +1482,6 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num, r = &pci_dev->io_regions[region_num]; assert(!r->size); - r->addr = PCI_BAR_UNMAPPED; r->size = size; r->type = type; r->memory = memory; @@ -1483,22 +1489,35 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num, ? pci_get_bus(pci_dev)->address_space_io : pci_get_bus(pci_dev)->address_space_mem; - wmask = ~(size - 1); - if (region_num == PCI_ROM_SLOT) { - /* ROM enable bit is writable */ - wmask |= PCI_ROM_ADDRESS_ENABLE; - } - - addr = pci_bar(pci_dev, region_num); - pci_set_long(pci_dev->config + addr, type); + if (pci_is_vf(pci_dev)) { + PCIDevice *pf = pci_dev->exp.sriov_vf.pf; + assert(!pf || type == pf->exp.sriov_pf.vf_bar_type[region_num]); - if (!(r->type & PCI_BASE_ADDRESS_SPACE_IO) && - r->type & PCI_BASE_ADDRESS_MEM_TYPE_64) { - pci_set_quad(pci_dev->wmask + addr, wmask); - pci_set_quad(pci_dev->cmask + addr, ~0ULL); + r->addr = pci_bar_address(pci_dev, region_num, r->type, r->size); + if (r->addr != PCI_BAR_UNMAPPED) { + memory_region_add_subregion_overlap(r->address_space, + r->addr, r->memory, 1); + } } else { - pci_set_long(pci_dev->wmask + addr, wmask & 0xffffffff); - pci_set_long(pci_dev->cmask + addr, 0xffffffff); + r->addr = PCI_BAR_UNMAPPED; + + wmask = ~(size - 1); + if (region_num == PCI_ROM_SLOT) { + /* ROM enable bit is writable */ + wmask |= PCI_ROM_ADDRESS_ENABLE; + } + + addr = pci_bar(pci_dev, region_num); + pci_set_long(pci_dev->config + addr, type); + + if (!(r->type & PCI_BASE_ADDRESS_SPACE_IO) && + r->type & PCI_BASE_ADDRESS_MEM_TYPE_64) { + pci_set_quad(pci_dev->wmask + addr, wmask); + pci_set_quad(pci_dev->cmask + addr, ~0ULL); + } else { + pci_set_long(pci_dev->wmask + addr, wmask & 0xffffffff); + pci_set_long(pci_dev->cmask + addr, 0xffffffff); + } } } @@ -1587,7 +1606,11 @@ static pcibus_t pci_config_get_bar_addr(PCIDevice *d, int reg, pci_get_word(pf->config + sriov_cap + PCI_SRIOV_VF_OFFSET); uint16_t vf_stride = pci_get_word(pf->config + sriov_cap + PCI_SRIOV_VF_STRIDE); - uint32_t vf_num = (d->devfn - (pf->devfn + vf_offset)) / vf_stride; + uint32_t vf_num = d->devfn - (pf->devfn + vf_offset); + + if (vf_num) { + vf_num /= vf_stride; + } if (type & PCI_BASE_ADDRESS_MEM_TYPE_64) { new_addr = pci_get_quad(pf->config + bar); @@ -1712,7 +1735,7 @@ static void pci_update_mappings(PCIDevice *d) pci_update_vga(d); } -static inline int pci_irq_disabled(PCIDevice *d) +int pci_irq_disabled(PCIDevice *d) { return pci_get_word(d->config + PCI_COMMAND) & PCI_COMMAND_INTX_DISABLE; } @@ -1774,9 +1797,8 @@ void pci_default_write_config(PCIDevice *d, uint32_t addr, uint32_t val_in, int if (ranges_overlap(addr, l, PCI_COMMAND, 2)) { pci_update_irq_disabled(d, was_irq_disabled); - memory_region_set_enabled(&d->bus_master_enable_region, - (pci_get_word(d->config + PCI_COMMAND) - & PCI_COMMAND_MASTER) && d->enabled); + pci_set_master(d, (pci_get_word(d->config + PCI_COMMAND) & + PCI_COMMAND_MASTER) && d->enabled); } msi_write_config(d, addr, val_in, l); @@ -2261,6 +2283,11 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp) } } + if (!pcie_sriov_register_device(pci_dev, errp)) { + pci_qdev_unrealize(DEVICE(pci_dev)); + return; + } + /* * A PCIe Downstream Port that do not have ARI Forwarding enabled must * associate only Device 0 with the device attached to the bus @@ -2515,6 +2542,14 @@ static void pci_add_option_rom(PCIDevice *pdev, bool is_default_rom, return; } + if (pci_is_vf(pdev)) { + if (pdev->rom_bar > 0) { + error_setg(errp, "ROM BAR cannot be enabled for SR-IOV VF"); + } + + return; + } + if (load_file || pdev->romsize == UINT32_MAX) { path = qemu_find_file(QEMU_FILE_TYPE_BIOS, pdev->romfile); if (path == NULL) { @@ -2909,6 +2944,23 @@ AddressSpace *pci_device_iommu_address_space(PCIDevice *dev) return &address_space_memory; } +int pci_iommu_init_iotlb_notifier(PCIDevice *dev, IOMMUNotifier *n, + IOMMUNotify fn, void *opaque) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->init_iotlb_notifier) { + iommu_bus->iommu_ops->init_iotlb_notifier(bus, iommu_bus->iommu_opaque, + devfn, n, fn, opaque); + return 0; + } + + return -ENODEV; +} + bool pci_device_set_iommu_device(PCIDevice *dev, HostIOMMUDevice *hiod, Error **errp) { @@ -2940,6 +2992,170 @@ void pci_device_unset_iommu_device(PCIDevice *dev) } } +int pci_pri_request_page(PCIDevice *dev, uint32_t pasid, bool priv_req, + bool exec_req, hwaddr addr, bool lpig, + uint16_t prgi, bool is_read, bool is_write) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + if (!dev->is_master || + ((pasid != PCI_NO_PASID) && !pcie_pasid_enabled(dev))) { + return -EPERM; + } + + if (!pcie_pri_enabled(dev)) { + return -EPERM; + } + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->pri_request_page) { + return iommu_bus->iommu_ops->pri_request_page(bus, + iommu_bus->iommu_opaque, + devfn, pasid, priv_req, + exec_req, addr, lpig, prgi, + is_read, is_write); + } + + return -ENODEV; +} + +int pci_pri_register_notifier(PCIDevice *dev, uint32_t pasid, + IOMMUPRINotifier *notifier) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + if (!dev->is_master || + ((pasid != PCI_NO_PASID) && !pcie_pasid_enabled(dev))) { + return -EPERM; + } + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->pri_register_notifier) { + iommu_bus->iommu_ops->pri_register_notifier(bus, + iommu_bus->iommu_opaque, + devfn, pasid, notifier); + return 0; + } + + return -ENODEV; +} + +void pci_pri_unregister_notifier(PCIDevice *dev, uint32_t pasid) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->pri_unregister_notifier) { + iommu_bus->iommu_ops->pri_unregister_notifier(bus, + iommu_bus->iommu_opaque, + devfn, pasid); + } +} + +ssize_t pci_ats_request_translation(PCIDevice *dev, uint32_t pasid, + bool priv_req, bool exec_req, + hwaddr addr, size_t length, + bool no_write, IOMMUTLBEntry *result, + size_t result_length, + uint32_t *err_count) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + if (!dev->is_master || + ((pasid != PCI_NO_PASID) && !pcie_pasid_enabled(dev))) { + return -EPERM; + } + + if (result_length == 0) { + return -ENOSPC; + } + + if (!pcie_ats_enabled(dev)) { + return -EPERM; + } + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->ats_request_translation) { + return iommu_bus->iommu_ops->ats_request_translation(bus, + iommu_bus->iommu_opaque, + devfn, pasid, priv_req, + exec_req, addr, length, + no_write, result, + result_length, err_count); + } + + return -ENODEV; +} + +int pci_iommu_register_iotlb_notifier(PCIDevice *dev, uint32_t pasid, + IOMMUNotifier *n) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + if ((pasid != PCI_NO_PASID) && !pcie_pasid_enabled(dev)) { + return -EPERM; + } + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->register_iotlb_notifier) { + iommu_bus->iommu_ops->register_iotlb_notifier(bus, + iommu_bus->iommu_opaque, devfn, + pasid, n); + return 0; + } + + return -ENODEV; +} + +int pci_iommu_unregister_iotlb_notifier(PCIDevice *dev, uint32_t pasid, + IOMMUNotifier *n) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + if ((pasid != PCI_NO_PASID) && !pcie_pasid_enabled(dev)) { + return -EPERM; + } + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->unregister_iotlb_notifier) { + iommu_bus->iommu_ops->unregister_iotlb_notifier(bus, + iommu_bus->iommu_opaque, + devfn, pasid, n); + return 0; + } + + return -ENODEV; +} + +int pci_iommu_get_iotlb_info(PCIDevice *dev, uint8_t *addr_width, + uint32_t *min_page_size) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->get_iotlb_info) { + iommu_bus->iommu_ops->get_iotlb_info(iommu_bus->iommu_opaque, + addr_width, min_page_size); + return 0; + } + + return -ENODEV; +} + void pci_setup_iommu(PCIBus *bus, const PCIIOMMUOps *ops, void *opaque) { /* @@ -3074,9 +3290,8 @@ void pci_set_enabled(PCIDevice *d, bool state) d->enabled = state; pci_update_mappings(d); - memory_region_set_enabled(&d->bus_master_enable_region, - (pci_get_word(d->config + PCI_COMMAND) - & PCI_COMMAND_MASTER) && d->enabled); + pci_set_master(d, (pci_get_word(d->config + PCI_COMMAND) + & PCI_COMMAND_MASTER) && d->enabled); if (qdev_is_realized(&d->qdev)) { pci_device_reset(d); } diff --git a/hw/pci/pci_host.c b/hw/pci/pci_host.c index abe83bb..7179d99 100644 --- a/hw/pci/pci_host.c +++ b/hw/pci/pci_host.c @@ -217,12 +217,6 @@ const MemoryRegionOps pci_host_data_le_ops = { .endianness = DEVICE_LITTLE_ENDIAN, }; -const MemoryRegionOps pci_host_data_be_ops = { - .read = pci_host_data_read, - .write = pci_host_data_write, - .endianness = DEVICE_BIG_ENDIAN, -}; - static bool pci_host_needed(void *opaque) { PCIHostState *s = opaque; diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c index 1b12db6..eaeb688 100644 --- a/hw/pci/pcie.c +++ b/hw/pci/pcie.c @@ -1214,3 +1214,81 @@ void pcie_acs_reset(PCIDevice *dev) pci_set_word(dev->config + dev->exp.acs_cap + PCI_ACS_CTRL, 0); } } + +/* PASID */ +void pcie_pasid_init(PCIDevice *dev, uint16_t offset, uint8_t pasid_width, + bool exec_perm, bool priv_mod) +{ + static const uint16_t control_reg_rw_mask = 0x07; + uint16_t capability_reg; + + assert(pasid_width <= PCI_EXT_CAP_PASID_MAX_WIDTH); + + pcie_add_capability(dev, PCI_EXT_CAP_ID_PASID, PCI_PASID_VER, offset, + PCI_EXT_CAP_PASID_SIZEOF); + + capability_reg = ((uint16_t)pasid_width) << PCI_PASID_CAP_WIDTH_SHIFT; + capability_reg |= exec_perm ? PCI_PASID_CAP_EXEC : 0; + capability_reg |= priv_mod ? PCI_PASID_CAP_PRIV : 0; + pci_set_word(dev->config + offset + PCI_PASID_CAP, capability_reg); + + /* Everything is disabled by default */ + pci_set_word(dev->config + offset + PCI_PASID_CTRL, 0); + + pci_set_word(dev->wmask + offset + PCI_PASID_CTRL, control_reg_rw_mask); + + dev->exp.pasid_cap = offset; +} + +/* PRI */ +void pcie_pri_init(PCIDevice *dev, uint16_t offset, uint32_t outstanding_pr_cap, + bool prg_response_pasid_req) +{ + static const uint16_t control_reg_rw_mask = 0x3; + static const uint16_t status_reg_rw1_mask = 0x3; + static const uint32_t pr_alloc_reg_rw_mask = 0xffffffff; + uint16_t status_reg; + + status_reg = prg_response_pasid_req ? PCI_PRI_STATUS_PASID : 0; + status_reg |= PCI_PRI_STATUS_STOPPED; /* Stopped by default */ + + pcie_add_capability(dev, PCI_EXT_CAP_ID_PRI, PCI_PRI_VER, offset, + PCI_EXT_CAP_PRI_SIZEOF); + /* Disabled by default */ + + pci_set_word(dev->config + offset + PCI_PRI_STATUS, status_reg); + pci_set_long(dev->config + offset + PCI_PRI_MAX_REQ, outstanding_pr_cap); + + pci_set_word(dev->wmask + offset + PCI_PRI_CTRL, control_reg_rw_mask); + pci_set_word(dev->w1cmask + offset + PCI_PRI_STATUS, status_reg_rw1_mask); + pci_set_long(dev->wmask + offset + PCI_PRI_ALLOC_REQ, pr_alloc_reg_rw_mask); + + dev->exp.pri_cap = offset; +} + +bool pcie_pri_enabled(const PCIDevice *dev) +{ + if (!pci_is_express(dev) || !dev->exp.pri_cap) { + return false; + } + return (pci_get_word(dev->config + dev->exp.pri_cap + PCI_PRI_CTRL) & + PCI_PRI_CTRL_ENABLE) != 0; +} + +bool pcie_pasid_enabled(const PCIDevice *dev) +{ + if (!pci_is_express(dev) || !dev->exp.pasid_cap) { + return false; + } + return (pci_get_word(dev->config + dev->exp.pasid_cap + PCI_PASID_CTRL) & + PCI_PASID_CTRL_ENABLE) != 0; +} + +bool pcie_ats_enabled(const PCIDevice *dev) +{ + if (!pci_is_express(dev) || !dev->exp.ats_cap) { + return false; + } + return (pci_get_word(dev->config + dev->exp.ats_cap + PCI_ATS_CTRL) & + PCI_ATS_CTRL_ENABLE) != 0; +} diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c index 1eb4358..8a4bf0d 100644 --- a/hw/pci/pcie_sriov.c +++ b/hw/pci/pcie_sriov.c @@ -15,11 +15,12 @@ #include "hw/pci/pcie.h" #include "hw/pci/pci_bus.h" #include "hw/qdev-properties.h" -#include "qemu/error-report.h" #include "qemu/range.h" #include "qapi/error.h" #include "trace.h" +static GHashTable *pfs; + static void unparent_vfs(PCIDevice *dev, uint16_t total_vfs) { for (uint16_t i = 0; i < total_vfs; i++) { @@ -31,17 +32,78 @@ static void unparent_vfs(PCIDevice *dev, uint16_t total_vfs) dev->exp.sriov_pf.vf = NULL; } -bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset, - const char *vfname, uint16_t vf_dev_id, - uint16_t init_vfs, uint16_t total_vfs, - uint16_t vf_offset, uint16_t vf_stride, - Error **errp) +static void register_vfs(PCIDevice *dev) +{ + uint16_t num_vfs; + uint16_t i; + uint16_t sriov_cap = dev->exp.sriov_cap; + + assert(sriov_cap > 0); + num_vfs = pci_get_word(dev->config + sriov_cap + PCI_SRIOV_NUM_VF); + + trace_sriov_register_vfs(dev->name, PCI_SLOT(dev->devfn), + PCI_FUNC(dev->devfn), num_vfs); + for (i = 0; i < num_vfs; i++) { + pci_set_enabled(dev->exp.sriov_pf.vf[i], true); + } + + pci_set_word(dev->wmask + sriov_cap + PCI_SRIOV_NUM_VF, 0); +} + +static void unregister_vfs(PCIDevice *dev) +{ + uint8_t *cfg = dev->config + dev->exp.sriov_cap; + uint16_t i; + + trace_sriov_unregister_vfs(dev->name, PCI_SLOT(dev->devfn), + PCI_FUNC(dev->devfn)); + for (i = 0; i < pci_get_word(cfg + PCI_SRIOV_TOTAL_VF); i++) { + pci_set_enabled(dev->exp.sriov_pf.vf[i], false); + } + + pci_set_word(dev->wmask + dev->exp.sriov_cap + PCI_SRIOV_NUM_VF, 0xffff); +} + +static void consume_config(PCIDevice *dev) +{ + uint8_t *cfg = dev->config + dev->exp.sriov_cap; + + if (pci_get_word(cfg + PCI_SRIOV_CTRL) & PCI_SRIOV_CTRL_VFE) { + register_vfs(dev); + } else { + uint8_t *wmask = dev->wmask + dev->exp.sriov_cap; + uint16_t num_vfs = pci_get_word(cfg + PCI_SRIOV_NUM_VF); + uint16_t wmask_val = PCI_SRIOV_CTRL_MSE | PCI_SRIOV_CTRL_ARI; + + unregister_vfs(dev); + + if (num_vfs <= pci_get_word(cfg + PCI_SRIOV_TOTAL_VF)) { + wmask_val |= PCI_SRIOV_CTRL_VFE; + } + + pci_set_word(wmask + PCI_SRIOV_CTRL, wmask_val); + } +} + +static bool pcie_sriov_pf_init_common(PCIDevice *dev, uint16_t offset, + uint16_t vf_dev_id, uint16_t init_vfs, + uint16_t total_vfs, uint16_t vf_offset, + uint16_t vf_stride, Error **errp) { - BusState *bus = qdev_get_parent_bus(&dev->qdev); int32_t devfn = dev->devfn + vf_offset; uint8_t *cfg = dev->config + offset; uint8_t *wmask; + if (!pci_is_express(dev)) { + error_setg(errp, "PCI Express is required for SR-IOV PF"); + return false; + } + + if (pci_is_vf(dev)) { + error_setg(errp, "a device cannot be a SR-IOV PF and a VF at the same time"); + return false; + } + if (total_vfs && (uint32_t)devfn + (uint32_t)(total_vfs - 1) * vf_stride >= PCI_DEVFN_MAX) { error_setg(errp, "VF addr overflows"); @@ -84,6 +146,28 @@ bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset, qdev_prop_set_bit(&dev->qdev, "multifunction", true); + return true; +} + +bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset, + const char *vfname, uint16_t vf_dev_id, + uint16_t init_vfs, uint16_t total_vfs, + uint16_t vf_offset, uint16_t vf_stride, + Error **errp) +{ + BusState *bus = qdev_get_parent_bus(&dev->qdev); + int32_t devfn = dev->devfn + vf_offset; + + if (pfs && g_hash_table_contains(pfs, dev->qdev.id)) { + error_setg(errp, "attaching user-created SR-IOV VF unsupported"); + return false; + } + + if (!pcie_sriov_pf_init_common(dev, offset, vf_dev_id, init_vfs, + total_vfs, vf_offset, vf_stride, errp)) { + return false; + } + dev->exp.sriov_pf.vf = g_new(PCIDevice *, total_vfs); for (uint16_t i = 0; i < total_vfs; i++) { @@ -113,7 +197,22 @@ void pcie_sriov_pf_exit(PCIDevice *dev) { uint8_t *cfg = dev->config + dev->exp.sriov_cap; - unparent_vfs(dev, pci_get_word(cfg + PCI_SRIOV_TOTAL_VF)); + if (dev->exp.sriov_pf.vf_user_created) { + uint16_t ven_id = pci_get_word(dev->config + PCI_VENDOR_ID); + uint16_t total_vfs = pci_get_word(dev->config + PCI_SRIOV_TOTAL_VF); + uint16_t vf_dev_id = pci_get_word(dev->config + PCI_SRIOV_VF_DID); + + unregister_vfs(dev); + + for (uint16_t i = 0; i < total_vfs; i++) { + dev->exp.sriov_pf.vf[i]->exp.sriov_vf.pf = NULL; + + pci_config_set_vendor_id(dev->exp.sriov_pf.vf[i]->config, ven_id); + pci_config_set_device_id(dev->exp.sriov_pf.vf[i]->config, vf_dev_id); + } + } else { + unparent_vfs(dev, pci_get_word(cfg + PCI_SRIOV_TOTAL_VF)); + } } void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num, @@ -146,69 +245,179 @@ void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num, void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num, MemoryRegion *memory) { - PCIIORegion *r; - PCIBus *bus = pci_get_bus(dev); uint8_t type; - pcibus_t size = memory_region_size(memory); - assert(pci_is_vf(dev)); /* PFs must use pci_register_bar */ - assert(region_num >= 0); - assert(region_num < PCI_NUM_REGIONS); + assert(dev->exp.sriov_vf.pf); type = dev->exp.sriov_vf.pf->exp.sriov_pf.vf_bar_type[region_num]; - if (!is_power_of_2(size)) { - error_report("%s: PCI region size must be a power" - " of two - type=0x%x, size=0x%"FMT_PCIBUS, - __func__, type, size); - exit(1); - } + return pci_register_bar(dev, region_num, type, memory); +} - r = &dev->io_regions[region_num]; - r->memory = memory; - r->address_space = - type & PCI_BASE_ADDRESS_SPACE_IO - ? bus->address_space_io - : bus->address_space_mem; - r->size = size; - r->type = type; - - r->addr = pci_bar_address(dev, region_num, r->type, r->size); - if (r->addr != PCI_BAR_UNMAPPED) { - memory_region_add_subregion_overlap(r->address_space, - r->addr, r->memory, 1); - } +static gint compare_vf_devfns(gconstpointer a, gconstpointer b) +{ + return (*(PCIDevice **)a)->devfn - (*(PCIDevice **)b)->devfn; } -static void register_vfs(PCIDevice *dev) +int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev, + uint16_t offset, + Error **errp) { - uint16_t num_vfs; + GPtrArray *pf; + PCIDevice **vfs; + BusState *bus = qdev_get_parent_bus(DEVICE(dev)); + uint16_t ven_id = pci_get_word(dev->config + PCI_VENDOR_ID); + uint16_t size = PCI_EXT_CAP_SRIOV_SIZEOF; + uint16_t vf_dev_id; + uint16_t vf_offset; + uint16_t vf_stride; uint16_t i; - uint16_t sriov_cap = dev->exp.sriov_cap; - assert(sriov_cap > 0); - num_vfs = pci_get_word(dev->config + sriov_cap + PCI_SRIOV_NUM_VF); + if (!pfs || !dev->qdev.id) { + return 0; + } - trace_sriov_register_vfs(dev->name, PCI_SLOT(dev->devfn), - PCI_FUNC(dev->devfn), num_vfs); - for (i = 0; i < num_vfs; i++) { - pci_set_enabled(dev->exp.sriov_pf.vf[i], true); + pf = g_hash_table_lookup(pfs, dev->qdev.id); + if (!pf) { + return 0; } - pci_set_word(dev->wmask + sriov_cap + PCI_SRIOV_NUM_VF, 0); + if (pf->len > UINT16_MAX) { + error_setg(errp, "too many VFs"); + return -1; + } + + g_ptr_array_sort(pf, compare_vf_devfns); + vfs = (void *)pf->pdata; + + if (vfs[0]->devfn <= dev->devfn) { + error_setg(errp, "a VF function number is less than the PF function number"); + return -1; + } + + vf_dev_id = pci_get_word(vfs[0]->config + PCI_DEVICE_ID); + vf_offset = vfs[0]->devfn - dev->devfn; + vf_stride = pf->len < 2 ? 0 : vfs[1]->devfn - vfs[0]->devfn; + + for (i = 0; i < pf->len; i++) { + if (bus != qdev_get_parent_bus(&vfs[i]->qdev)) { + error_setg(errp, "SR-IOV VF parent bus mismatches with PF"); + return -1; + } + + if (ven_id != pci_get_word(vfs[i]->config + PCI_VENDOR_ID)) { + error_setg(errp, "SR-IOV VF vendor ID mismatches with PF"); + return -1; + } + + if (vf_dev_id != pci_get_word(vfs[i]->config + PCI_DEVICE_ID)) { + error_setg(errp, "inconsistent SR-IOV VF device IDs"); + return -1; + } + + for (size_t j = 0; j < PCI_NUM_REGIONS; j++) { + if (vfs[i]->io_regions[j].size != vfs[0]->io_regions[j].size || + vfs[i]->io_regions[j].type != vfs[0]->io_regions[j].type) { + error_setg(errp, "inconsistent SR-IOV BARs"); + return -1; + } + } + + if (vfs[i]->devfn - vfs[0]->devfn != vf_stride * i) { + error_setg(errp, "inconsistent SR-IOV stride"); + return -1; + } + } + + if (!pcie_sriov_pf_init_common(dev, offset, vf_dev_id, pf->len, + pf->len, vf_offset, vf_stride, errp)) { + return -1; + } + + if (!pcie_find_capability(dev, PCI_EXT_CAP_ID_ARI)) { + pcie_ari_init(dev, offset + size); + size += PCI_ARI_SIZEOF; + } + + for (i = 0; i < pf->len; i++) { + vfs[i]->exp.sriov_vf.pf = dev; + vfs[i]->exp.sriov_vf.vf_number = i; + + /* set vid/did according to sr/iov spec - they are not used */ + pci_config_set_vendor_id(vfs[i]->config, 0xffff); + pci_config_set_device_id(vfs[i]->config, 0xffff); + } + + dev->exp.sriov_pf.vf = vfs; + dev->exp.sriov_pf.vf_user_created = true; + + for (i = 0; i < PCI_NUM_REGIONS; i++) { + PCIIORegion *region = &vfs[0]->io_regions[i]; + + if (region->size) { + pcie_sriov_pf_init_vf_bar(dev, i, region->type, region->size); + } + } + + return size; } -static void unregister_vfs(PCIDevice *dev) +bool pcie_sriov_register_device(PCIDevice *dev, Error **errp) { - uint8_t *cfg = dev->config + dev->exp.sriov_cap; - uint16_t i; + if (!dev->exp.sriov_pf.vf && dev->qdev.id && + pfs && g_hash_table_contains(pfs, dev->qdev.id)) { + error_setg(errp, "attaching user-created SR-IOV VF unsupported"); + return false; + } - trace_sriov_unregister_vfs(dev->name, PCI_SLOT(dev->devfn), - PCI_FUNC(dev->devfn)); - for (i = 0; i < pci_get_word(cfg + PCI_SRIOV_TOTAL_VF); i++) { - pci_set_enabled(dev->exp.sriov_pf.vf[i], false); + if (dev->sriov_pf) { + PCIDevice *pci_pf; + GPtrArray *pf; + + if (!PCI_DEVICE_GET_CLASS(dev)->sriov_vf_user_creatable) { + error_setg(errp, "user cannot create SR-IOV VF with this device type"); + return false; + } + + if (!pci_is_express(dev)) { + error_setg(errp, "PCI Express is required for SR-IOV VF"); + return false; + } + + if (!pci_qdev_find_device(dev->sriov_pf, &pci_pf)) { + error_setg(errp, "PCI device specified as SR-IOV PF already exists"); + return false; + } + + if (!pfs) { + pfs = g_hash_table_new_full(g_str_hash, g_str_equal, g_free, NULL); + } + + pf = g_hash_table_lookup(pfs, dev->sriov_pf); + if (!pf) { + pf = g_ptr_array_new(); + g_hash_table_insert(pfs, g_strdup(dev->sriov_pf), pf); + } + + g_ptr_array_add(pf, dev); } - pci_set_word(dev->wmask + dev->exp.sriov_cap + PCI_SRIOV_NUM_VF, 0xffff); + return true; +} + +void pcie_sriov_unregister_device(PCIDevice *dev) +{ + if (dev->sriov_pf && pfs) { + GPtrArray *pf = g_hash_table_lookup(pfs, dev->sriov_pf); + + if (pf) { + g_ptr_array_remove_fast(pf, dev); + + if (!pf->len) { + g_hash_table_remove(pfs, dev->sriov_pf); + g_ptr_array_free(pf, FALSE); + } + } + } } void pcie_sriov_config_write(PCIDevice *dev, uint32_t address, @@ -228,30 +437,13 @@ void pcie_sriov_config_write(PCIDevice *dev, uint32_t address, trace_sriov_config_write(dev->name, PCI_SLOT(dev->devfn), PCI_FUNC(dev->devfn), off, val, len); - if (range_covers_byte(off, len, PCI_SRIOV_CTRL)) { - if (val & PCI_SRIOV_CTRL_VFE) { - register_vfs(dev); - } else { - unregister_vfs(dev); - } - } else if (range_covers_byte(off, len, PCI_SRIOV_NUM_VF)) { - uint8_t *cfg = dev->config + sriov_cap; - uint8_t *wmask = dev->wmask + sriov_cap; - uint16_t num_vfs = pci_get_word(cfg + PCI_SRIOV_NUM_VF); - uint16_t wmask_val = PCI_SRIOV_CTRL_MSE | PCI_SRIOV_CTRL_ARI; - - if (num_vfs <= pci_get_word(cfg + PCI_SRIOV_TOTAL_VF)) { - wmask_val |= PCI_SRIOV_CTRL_VFE; - } - - pci_set_word(wmask + PCI_SRIOV_CTRL, wmask_val); - } + consume_config(dev); } void pcie_sriov_pf_post_load(PCIDevice *dev) { if (dev->exp.sriov_cap) { - register_vfs(dev); + consume_config(dev); } } @@ -304,7 +496,7 @@ void pcie_sriov_pf_add_sup_pgsize(PCIDevice *dev, uint16_t opt_sup_pgsize) uint16_t pcie_sriov_vf_number(PCIDevice *dev) { - assert(pci_is_vf(dev)); + assert(dev->exp.sriov_vf.pf); return dev->exp.sriov_vf.vf_number; } |