1 files changed, 308 insertions, 105 deletions

diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c
index e9b2322..3ad1874 100644
--- a/hw/pci/pcie_sriov.c
+++ b/hw/pci/pcie_sriov.c
@@ -15,28 +15,83 @@
 #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 PCIDevice *register_vf(PCIDevice *pf, int devfn,
-                              const char *name, uint16_t vf_num);
-static void unregister_vfs(PCIDevice *dev);
+static GHashTable *pfs;
 
-void 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)
+static void unparent_vfs(PCIDevice *dev, uint16_t total_vfs)
+{
+    for (uint16_t i = 0; i < total_vfs; i++) {
+        PCIDevice *vf = dev->exp.sriov_pf.vf[i];
+        object_unparent(OBJECT(vf));
+        object_unref(OBJECT(vf));
+    }
+    g_free(dev->exp.sriov_pf.vf);
+    dev->exp.sriov_pf.vf = NULL;
+}
+
+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 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)
 {
+    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");
+        return false;
+    }
+
     pcie_add_capability(dev, PCI_EXT_CAP_ID_SRIOV, 1,
                         offset, PCI_EXT_CAP_SRIOV_SIZEOF);
     dev->exp.sriov_cap = offset;
-    dev->exp.sriov_pf.num_vfs = 0;
-    dev->exp.sriov_pf.vfname = g_strdup(vfname);
     dev->exp.sriov_pf.vf = NULL;
 
     pci_set_word(cfg + PCI_SRIOV_VF_OFFSET, vf_offset);
@@ -69,13 +124,74 @@ void pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
     pci_set_word(wmask + PCI_SRIOV_SYS_PGSIZE, 0x553);
 
     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++) {
+        PCIDevice *vf = pci_new(devfn, vfname);
+        vf->exp.sriov_vf.pf = dev;
+        vf->exp.sriov_vf.vf_number = i;
+
+        if (!qdev_realize(&vf->qdev, bus, errp)) {
+            object_unparent(OBJECT(vf));
+            object_unref(vf);
+            unparent_vfs(dev, i);
+            return false;
+        }
+
+        /* set vid/did according to sr/iov spec - they are not used */
+        pci_config_set_vendor_id(vf->config, 0xffff);
+        pci_config_set_device_id(vf->config, 0xffff);
+
+        dev->exp.sriov_pf.vf[i] = vf;
+        devfn += vf_stride;
+    }
+
+    return true;
 }
 
 void pcie_sriov_pf_exit(PCIDevice *dev)
 {
-    unregister_vfs(dev);
-    g_free((char *)dev->exp.sriov_pf.vfname);
-    dev->exp.sriov_pf.vfname = NULL;
+    uint8_t *cfg = dev->config + dev->exp.sriov_cap;
+
+    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,
@@ -108,113 +224,179 @@ 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 PCIDevice *register_vf(PCIDevice *pf, int devfn, const char *name,
-                              uint16_t vf_num)
+int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,
+                                                 uint16_t offset,
+                                                 Error **errp)
 {
-    PCIDevice *dev = pci_new(devfn, name);
-    dev->exp.sriov_vf.pf = pf;
-    dev->exp.sriov_vf.vf_number = vf_num;
-    PCIBus *bus = pci_get_bus(pf);
-    Error *local_err = NULL;
-
-    qdev_realize(&dev->qdev, &bus->qbus, &local_err);
-    if (local_err) {
-        error_report_err(local_err);
-        return NULL;
+    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;
+
+    if (!pfs || !dev->qdev.id) {
+        return 0;
+    }
+
+    pf = g_hash_table_lookup(pfs, dev->qdev.id);
+    if (!pf) {
+        return 0;
+    }
+
+    if (pf->len > UINT16_MAX) {
+        error_setg(errp, "too many VFs");
+        return -1;
     }
 
-    /* set vid/did according to sr/iov spec - they are not used */
-    pci_config_set_vendor_id(dev->config, 0xffff);
-    pci_config_set_device_id(dev->config, 0xffff);
+    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;
+        }
 
-    return dev;
+        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 register_vfs(PCIDevice *dev)
+bool pcie_sriov_register_device(PCIDevice *dev, Error **errp)
 {
-    uint16_t num_vfs;
-    uint16_t i;
-    uint16_t sriov_cap = dev->exp.sriov_cap;
-    uint16_t vf_offset =
-        pci_get_word(dev->config + sriov_cap + PCI_SRIOV_VF_OFFSET);
-    uint16_t vf_stride =
-        pci_get_word(dev->config + sriov_cap + PCI_SRIOV_VF_STRIDE);
-    int32_t devfn = dev->devfn + vf_offset;
-
-    assert(sriov_cap > 0);
-    num_vfs = pci_get_word(dev->config + sriov_cap + PCI_SRIOV_NUM_VF);
-    if (num_vfs > pci_get_word(dev->config + sriov_cap + PCI_SRIOV_TOTAL_VF)) {
-        return;
+    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;
     }
 
-    dev->exp.sriov_pf.vf = g_new(PCIDevice *, num_vfs);
+    if (dev->sriov_pf) {
+        PCIDevice *pci_pf;
+        GPtrArray *pf;
 
-    trace_sriov_register_vfs(dev->name, PCI_SLOT(dev->devfn),
-                             PCI_FUNC(dev->devfn), num_vfs);
-    for (i = 0; i < num_vfs; i++) {
-        dev->exp.sriov_pf.vf[i] = register_vf(dev, devfn,
-                                              dev->exp.sriov_pf.vfname, i);
-        if (!dev->exp.sriov_pf.vf[i]) {
-            num_vfs = i;
-            break;
+        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;
         }
-        devfn += vf_stride;
+
+        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);
     }
-    dev->exp.sriov_pf.num_vfs = num_vfs;
+
+    return true;
 }
 
-static void unregister_vfs(PCIDevice *dev)
+void pcie_sriov_unregister_device(PCIDevice *dev)
 {
-    uint16_t num_vfs = dev->exp.sriov_pf.num_vfs;
-    uint16_t i;
+    if (dev->sriov_pf && pfs) {
+        GPtrArray *pf = g_hash_table_lookup(pfs, dev->sriov_pf);
 
-    trace_sriov_unregister_vfs(dev->name, PCI_SLOT(dev->devfn),
-                               PCI_FUNC(dev->devfn), num_vfs);
-    for (i = 0; i < num_vfs; i++) {
-        Error *err = NULL;
-        PCIDevice *vf = dev->exp.sriov_pf.vf[i];
-        if (!object_property_set_bool(OBJECT(vf), "realized", false, &err)) {
-            error_reportf_err(err, "Failed to unplug: ");
+        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);
+            }
         }
-        object_unparent(OBJECT(vf));
-        object_unref(OBJECT(vf));
     }
-    g_free(dev->exp.sriov_pf.vf);
-    dev->exp.sriov_pf.vf = NULL;
-    dev->exp.sriov_pf.num_vfs = 0;
 }
 
 void pcie_sriov_config_write(PCIDevice *dev, uint32_t address,
@@ -235,15 +417,29 @@ void pcie_sriov_config_write(PCIDevice *dev, uint32_t address,
                              PCI_FUNC(dev->devfn), off, val, len);
 
     if (range_covers_byte(off, len, PCI_SRIOV_CTRL)) {
-        if (dev->exp.sriov_pf.num_vfs) {
-            if (!(val & PCI_SRIOV_CTRL_VFE)) {
-                unregister_vfs(dev);
-            }
+        if (val & PCI_SRIOV_CTRL_VFE) {
+            register_vfs(dev);
         } else {
-            if (val & PCI_SRIOV_CTRL_VFE) {
-                register_vfs(dev);
-            }
+            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);
+    }
+}
+
+void pcie_sriov_pf_post_load(PCIDevice *dev)
+{
+    if (dev->exp.sriov_cap) {
+        register_vfs(dev);
     }
 }
 
@@ -260,6 +456,8 @@ void pcie_sriov_pf_reset(PCIDevice *dev)
     unregister_vfs(dev);
 
     pci_set_word(dev->config + sriov_cap + PCI_SRIOV_NUM_VF, 0);
+    pci_set_word(dev->wmask + sriov_cap + PCI_SRIOV_CTRL,
+                 PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE | PCI_SRIOV_CTRL_ARI);
 
     /*
      * Default is to use 4K pages, software can modify it
@@ -294,7 +492,7 @@ 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;
 }
 
@@ -306,7 +504,7 @@ PCIDevice *pcie_sriov_get_pf(PCIDevice *dev)
 PCIDevice *pcie_sriov_get_vf_at_index(PCIDevice *dev, int n)
 {
     assert(!pci_is_vf(dev));
-    if (n < dev->exp.sriov_pf.num_vfs) {
+    if (n < pcie_sriov_num_vfs(dev)) {
         return dev->exp.sriov_pf.vf[n];
     }
     return NULL;
@@ -314,5 +512,10 @@ PCIDevice *pcie_sriov_get_vf_at_index(PCIDevice *dev, int n)
 
 uint16_t pcie_sriov_num_vfs(PCIDevice *dev)
 {
-    return dev->exp.sriov_pf.num_vfs;
+    uint16_t sriov_cap = dev->exp.sriov_cap;
+    uint8_t *cfg = dev->config + sriov_cap;
+
+    return sriov_cap &&
+           (pci_get_word(cfg + PCI_SRIOV_CTRL) & PCI_SRIOV_CTRL_VFE) ?
+           pci_get_word(cfg + PCI_SRIOV_NUM_VF) : 0;
 }