[PATCH 0/6] hw/pci: SR-IOV related fixes and improvements

[PATCH 0/6] hw/pci: SR-IOV related fixes and improvements

[Akihiko Odaki]

I submitted a RFC series[1] to add support for SR-IOV emulation to
virtio-net-pci. During the development of the series, I fixed some
trivial bugs and made improvements that I think are independently
useful. This series extracts those fixes and improvements from the RFC
series. Below is an explanation of the patches:

Patch 1 adds a function to check if ROM BAR is explicitly enabled. It
is used in the RFC series to report an error if the user requests to
enable ROM BAR for SR-IOV VF. Patch 2 and 3 use it for vfio to remove
hacky device option dictionary inspection.

Patch 4 adds SR-IOV NumVFs validation to fix potential buffer overflow.

Patch 5 changes to realize SR-IOV VFs when the PF is being realized to
validate VF configuration.

Patch 6 fixes memory leak that occurs if a SR-IOV VF fails to realize.

[1]: https://patchew.org/QEMU/20231210-sriov-v2-0-b959e8a6dfaf@daynix.com/

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
---
Akihiko Odaki (6):
      hw/pci: Determine if rombar is explicitly enabled
      vfio: Avoid inspecting option QDict for rombar
      hw/qdev: Remove opts member
      pcie_sriov: Validate NumVFs
      pcie_sriov: Reuse SR-IOV VF device instances
      pcie_sriov: Release VFs failed to realize

 docs/pcie_sriov.txt         |   8 ++--
 include/hw/pci/pci.h        |   2 +-
 include/hw/pci/pci_device.h |   7 ++-
 include/hw/pci/pcie_sriov.h |   6 +--
 include/hw/qdev-core.h      |   4 --
 hw/core/qdev.c              |   1 -
 hw/net/igb.c                |  13 ++++--
 hw/nvme/ctrl.c              |  29 ++++++------
 hw/pci/pci.c                |  20 +++++----
 hw/pci/pci_host.c           |   4 +-
 hw/pci/pcie.c               |   4 +-
 hw/pci/pcie_sriov.c         | 105 +++++++++++++++++++++-----------------------
 hw/vfio/pci.c               |   3 +-
 system/qdev-monitor.c       |  12 ++---
 14 files changed, 116 insertions(+), 102 deletions(-)
---
base-commit: 4a4efae44f19528589204581e9e2fab69c5d39aa
change-id: 20240129-reuse-faae22b11934

Best regards,
-- 
Akihiko Odaki <akihiko.odaki@daynix.com>

[PATCH 1/6] hw/pci: Determine if rombar is explicitly enabled

[Akihiko Odaki]

vfio determines if rombar is explicitly enabled by inspecting QDict.
Inspecting QDict is not nice because QDict is untyped and depends on the
details on the external interface. Add an infrastructure to determine if
rombar is explicitly enabled to hw/pci. PCIDevice::rom_bar is changed to
have -1 by the default to tell rombar is explicitly enabled. It is
consistent with other properties like addr and romsize.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
---
 include/hw/pci/pci_device.h | 5 +++++
 hw/pci/pci.c                | 2 +-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/include/hw/pci/pci_device.h b/include/hw/pci/pci_device.h
index d3dd0f64b273..54fa0676abf1 100644
--- a/include/hw/pci/pci_device.h
+++ b/include/hw/pci/pci_device.h
@@ -205,6 +205,11 @@ static inline uint16_t pci_get_bdf(PCIDevice *dev)
     return PCI_BUILD_BDF(pci_bus_num(pci_get_bus(dev)), dev->devfn);
 }
 
+static inline bool pci_rom_bar_explicitly_enabled(PCIDevice *dev)
+{
+    return dev->rom_bar && dev->rom_bar != -1;
+}
+
 uint16_t pci_requester_id(PCIDevice *dev);
 
 /* DMA access functions */
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index 76080af580d7..d08548d8ffe9 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -71,7 +71,7 @@ static Property pci_props[] = {
     DEFINE_PROP_PCI_DEVFN("addr", PCIDevice, devfn, -1),
     DEFINE_PROP_STRING("romfile", PCIDevice, romfile),
     DEFINE_PROP_UINT32("romsize", PCIDevice, romsize, -1),
-    DEFINE_PROP_UINT32("rombar",  PCIDevice, rom_bar, 1),
+    DEFINE_PROP_UINT32("rombar",  PCIDevice, rom_bar, -1),
     DEFINE_PROP_BIT("multifunction", PCIDevice, cap_present,
                     QEMU_PCI_CAP_MULTIFUNCTION_BITNR, false),
     DEFINE_PROP_BIT("x-pcie-lnksta-dllla", PCIDevice, cap_present,

-- 
2.43.0

[PATCH 2/6] vfio: Avoid inspecting option QDict for rombar

[Akihiko Odaki]

Use pci_rom_bar_explicitly_enabled() to determine if rombar is explicitly
enabled.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
---
 hw/vfio/pci.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index d7fe06715c4b..44178ac9355f 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -1010,7 +1010,6 @@ static void vfio_pci_size_rom(VFIOPCIDevice *vdev)
 {
     uint32_t orig, size = cpu_to_le32((uint32_t)PCI_ROM_ADDRESS_MASK);
     off_t offset = vdev->config_offset + PCI_ROM_ADDRESS;
-    DeviceState *dev = DEVICE(vdev);
     char *name;
     int fd = vdev->vbasedev.fd;
 
@@ -1044,7 +1043,7 @@ static void vfio_pci_size_rom(VFIOPCIDevice *vdev)
     }
 
     if (vfio_opt_rom_in_denylist(vdev)) {
-        if (dev->opts && qdict_haskey(dev->opts, "rombar")) {
+        if (pci_rom_bar_explicitly_enabled(&vdev->pdev)) {
             warn_report("Device at %s is known to cause system instability"
                         " issues during option rom execution",
                         vdev->vbasedev.name);

-- 
2.43.0

[PATCH 3/6] hw/qdev: Remove opts member

[Akihiko Odaki]

It is no longer used.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
---
 include/hw/qdev-core.h |  4 ----
 hw/core/qdev.c         |  1 -
 system/qdev-monitor.c  | 12 +++++++-----
 3 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
index 151d9682380d..6befbca31117 100644
--- a/include/hw/qdev-core.h
+++ b/include/hw/qdev-core.h
@@ -237,10 +237,6 @@ struct DeviceState {
      * @pending_deleted_expires_ms: optional timeout for deletion events
      */
     int64_t pending_deleted_expires_ms;
-    /**
-     * @opts: QDict of options for the device
-     */
-    QDict *opts;
     /**
      * @hotplugged: was device added after PHASE_MACHINE_READY?
      */
diff --git a/hw/core/qdev.c b/hw/core/qdev.c
index 43d863b0c5b0..c98691a90d48 100644
--- a/hw/core/qdev.c
+++ b/hw/core/qdev.c
@@ -706,7 +706,6 @@ static void device_finalize(Object *obj)
         dev->canonical_path = NULL;
     }
 
-    qobject_unref(dev->opts);
     g_free(dev->id);
 }
 
diff --git a/system/qdev-monitor.c b/system/qdev-monitor.c
index a13db763e5dd..71c00f62ee38 100644
--- a/system/qdev-monitor.c
+++ b/system/qdev-monitor.c
@@ -625,6 +625,7 @@ DeviceState *qdev_device_add_from_qdict(const QDict *opts,
     char *id;
     DeviceState *dev = NULL;
     BusState *bus = NULL;
+    QDict *properties;
 
     driver = qdict_get_try_str(opts, "driver");
     if (!driver) {
@@ -705,13 +706,14 @@ DeviceState *qdev_device_add_from_qdict(const QDict *opts,
     }
 
     /* set properties */
-    dev->opts = qdict_clone_shallow(opts);
-    qdict_del(dev->opts, "driver");
-    qdict_del(dev->opts, "bus");
-    qdict_del(dev->opts, "id");
+    properties = qdict_clone_shallow(opts);
+    qdict_del(properties, "driver");
+    qdict_del(properties, "bus");
+    qdict_del(properties, "id");
 
-    object_set_properties_from_keyval(&dev->parent_obj, dev->opts, from_json,
+    object_set_properties_from_keyval(&dev->parent_obj, properties, from_json,
                                       errp);
+    qobject_unref(properties);
     if (*errp) {
         goto err_del_dev;
     }

-- 
2.43.0

[PATCH 4/6] pcie_sriov: Validate NumVFs

[Akihiko Odaki]

The guest may write NumVFs greater than TotalVFs and that can lead
to buffer overflow in VF implementations.

Fixes: 7c0fa8dff811 ("pcie: Add support for Single Root I/O Virtualization (SR/IOV)")
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
---
 hw/pci/pcie_sriov.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c
index a1fe65f5d801..da209b7f47fd 100644
--- a/hw/pci/pcie_sriov.c
+++ b/hw/pci/pcie_sriov.c
@@ -176,6 +176,9 @@ static void register_vfs(PCIDevice *dev)
 
     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;
+    }
 
     dev->exp.sriov_pf.vf = g_new(PCIDevice *, num_vfs);
 

-- 
2.43.0

[PATCH 5/6] pcie_sriov: Reuse SR-IOV VF device instances

[Akihiko Odaki]

Disable SR-IOV VF devices by reusing code to power down PCI devices
instead of removing them when the guest requests to disable VFs. This
allows to realize devices and report VF realization errors at PF
realization time.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
---
 docs/pcie_sriov.txt         |   8 ++--
 include/hw/pci/pci.h        |   2 +-
 include/hw/pci/pci_device.h |   2 +-
 include/hw/pci/pcie_sriov.h |   6 +--
 hw/net/igb.c                |  13 ++++--
 hw/nvme/ctrl.c              |  29 +++++++------
 hw/pci/pci.c                |  18 ++++----
 hw/pci/pci_host.c           |   4 +-
 hw/pci/pcie.c               |   4 +-
 hw/pci/pcie_sriov.c         | 100 ++++++++++++++++++++------------------------
 10 files changed, 97 insertions(+), 89 deletions(-)

diff --git a/docs/pcie_sriov.txt b/docs/pcie_sriov.txt
index a47aad0bfab0..ab2142807f79 100644
--- a/docs/pcie_sriov.txt
+++ b/docs/pcie_sriov.txt
@@ -52,9 +52,11 @@ setting up a BAR for a VF.
       ...
 
       /* Add and initialize the SR/IOV capability */
-      pcie_sriov_pf_init(d, 0x200, "your_virtual_dev",
-                       vf_devid, initial_vfs, total_vfs,
-                       fun_offset, stride);
+      if (!pcie_sriov_pf_init(d, 0x200, "your_virtual_dev",
+                              vf_devid, initial_vfs, total_vfs,
+                              fun_offset, stride, errp)) {
+         return;
+      }
 
       /* Set up individual VF BARs (parameters as for normal BARs) */
       pcie_sriov_pf_init_vf_bar( ... )
diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index fa6313aabc43..fae83b9b723c 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -643,6 +643,6 @@ static inline void pci_irq_pulse(PCIDevice *pci_dev)
 }
 
 MSIMessage pci_get_msi_message(PCIDevice *dev, int vector);
-void pci_set_power(PCIDevice *pci_dev, bool state);
+void pci_set_enabled(PCIDevice *pci_dev, bool state);
 
 #endif
diff --git a/include/hw/pci/pci_device.h b/include/hw/pci/pci_device.h
index 54fa0676abf1..f5aba8ae2675 100644
--- a/include/hw/pci/pci_device.h
+++ b/include/hw/pci/pci_device.h
@@ -56,7 +56,7 @@ typedef struct PCIReqIDCache PCIReqIDCache;
 struct PCIDevice {
     DeviceState qdev;
     bool partially_hotplugged;
-    bool has_power;
+    bool is_enabled;
 
     /* PCI config space */
     uint8_t *config;
diff --git a/include/hw/pci/pcie_sriov.h b/include/hw/pci/pcie_sriov.h
index 095fb0c9edf9..d9a39daccac4 100644
--- a/include/hw/pci/pcie_sriov.h
+++ b/include/hw/pci/pcie_sriov.h
@@ -18,7 +18,6 @@
 struct PCIESriovPF {
     uint16_t num_vfs;   /* Number of virtual functions created */
     uint8_t vf_bar_type[PCI_NUM_REGIONS];   /* Store type for each VF bar */
-    const char *vfname; /* Reference to the device type used for the VFs */
     PCIDevice **vf;     /* Pointer to an array of num_vfs VF devices */
 };
 
@@ -27,10 +26,11 @@ struct PCIESriovVF {
     uint16_t vf_number; /* Logical VF number of this function */
 };
 
-void pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
+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);
+                        uint16_t vf_offset, uint16_t vf_stride,
+                        Error **errp);
 void pcie_sriov_pf_exit(PCIDevice *dev);
 
 /* Set up a VF bar in the SR/IOV bar area */
diff --git a/hw/net/igb.c b/hw/net/igb.c
index 0b5c31a58bba..1079a33d4000 100644
--- a/hw/net/igb.c
+++ b/hw/net/igb.c
@@ -447,9 +447,16 @@ static void igb_pci_realize(PCIDevice *pci_dev, Error **errp)
 
     pcie_ari_init(pci_dev, 0x150);
 
-    pcie_sriov_pf_init(pci_dev, IGB_CAP_SRIOV_OFFSET, TYPE_IGBVF,
-        IGB_82576_VF_DEV_ID, IGB_MAX_VF_FUNCTIONS, IGB_MAX_VF_FUNCTIONS,
-        IGB_VF_OFFSET, IGB_VF_STRIDE);
+    if (!pcie_sriov_pf_init(pci_dev, IGB_CAP_SRIOV_OFFSET,
+                            TYPE_IGBVF, IGB_82576_VF_DEV_ID,
+                            IGB_MAX_VF_FUNCTIONS, IGB_MAX_VF_FUNCTIONS,
+                            IGB_VF_OFFSET, IGB_VF_STRIDE,
+                            errp)) {
+        pcie_cap_exit(pci_dev);
+        igb_cleanup_msix(s);
+        msi_uninit(pci_dev);
+        return;
+    }
 
     pcie_sriov_pf_init_vf_bar(pci_dev, IGBVF_MMIO_BAR_IDX,
         PCI_BASE_ADDRESS_MEM_TYPE_64 | PCI_BASE_ADDRESS_MEM_PREFETCH,
diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c
index f026245d1e9e..a356a452ad47 100644
--- a/hw/nvme/ctrl.c
+++ b/hw/nvme/ctrl.c
@@ -8031,7 +8031,8 @@ static uint64_t nvme_bar_size(unsigned total_queues, unsigned total_irqs,
     return bar_size;
 }
 
-static void nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset)
+static bool nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset,
+                            Error **errp)
 {
     uint16_t vf_dev_id = n->params.use_intel_id ?
                          PCI_DEVICE_ID_INTEL_NVME : PCI_DEVICE_ID_REDHAT_NVME;
@@ -8040,12 +8041,17 @@ static void nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset)
                                       le16_to_cpu(cap->vifrsm),
                                       NULL, NULL);
 
-    pcie_sriov_pf_init(pci_dev, offset, "nvme", vf_dev_id,
-                       n->params.sriov_max_vfs, n->params.sriov_max_vfs,
-                       NVME_VF_OFFSET, NVME_VF_STRIDE);
+    if (!pcie_sriov_pf_init(pci_dev, offset, "nvme", vf_dev_id,
+                            n->params.sriov_max_vfs, n->params.sriov_max_vfs,
+                            NVME_VF_OFFSET, NVME_VF_STRIDE,
+                            errp)) {
+        return false;
+    }
 
     pcie_sriov_pf_init_vf_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
                               PCI_BASE_ADDRESS_MEM_TYPE_64, bar_size);
+
+    return true;
 }
 
 static int nvme_add_pm_capability(PCIDevice *pci_dev, uint8_t offset)
@@ -8124,6 +8130,12 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
         return false;
     }
 
+    if (!pci_is_vf(pci_dev) && n->params.sriov_max_vfs &&
+        !nvme_init_sriov(n, pci_dev, 0x120, errp)) {
+        msix_uninit(pci_dev, &n->bar0, &n->bar0);
+        return false;
+    }
+
     nvme_update_msixcap_ts(pci_dev, n->conf_msix_qsize);
 
     if (n->params.cmb_size_mb) {
@@ -8134,10 +8146,6 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
         nvme_init_pmr(n, pci_dev);
     }
 
-    if (!pci_is_vf(pci_dev) && n->params.sriov_max_vfs) {
-        nvme_init_sriov(n, pci_dev, 0x120);
-    }
-
     return true;
 }
 
@@ -8159,7 +8167,6 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev)
     NvmeIdCtrl *id = &n->id_ctrl;
     uint8_t *pci_conf = pci_dev->config;
     uint64_t cap = ldq_le_p(&n->bar.cap);
-    NvmeSecCtrlEntry *sctrl = nvme_sctrl(n);
     uint32_t ctratt;
 
     id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID));
@@ -8263,10 +8270,6 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev)
 
     stl_le_p(&n->bar.vs, NVME_SPEC_VER);
     n->bar.intmc = n->bar.intms = 0;
-
-    if (pci_is_vf(pci_dev) && !sctrl->scs) {
-        stl_le_p(&n->bar.csts, NVME_CSTS_FAILED);
-    }
 }
 
 static int nvme_init_subsys(NvmeCtrl *n, Error **errp)
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index d08548d8ffe9..a72a2d47b840 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -1522,7 +1522,7 @@ static void pci_update_mappings(PCIDevice *d)
             continue;
 
         new_addr = pci_bar_address(d, i, r->type, r->size);
-        if (!d->has_power) {
+        if (!d->is_enabled) {
             new_addr = PCI_BAR_UNMAPPED;
         }
 
@@ -1610,7 +1610,7 @@ void pci_default_write_config(PCIDevice *d, uint32_t addr, uint32_t val_in, int
         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->has_power);
+                                   & PCI_COMMAND_MASTER) && d->is_enabled);
     }
 
     msi_write_config(d, addr, val_in, l);
@@ -2179,7 +2179,9 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp)
         return;
     }
 
-    pci_set_power(pci_dev, true);
+    if (!pci_is_vf(pci_dev)) {
+        pci_set_enabled(pci_dev, true);
+    }
 
     pci_dev->msi_trigger = pci_msi_trigger;
 }
@@ -2835,18 +2837,18 @@ MSIMessage pci_get_msi_message(PCIDevice *dev, int vector)
     return msg;
 }
 
-void pci_set_power(PCIDevice *d, bool state)
+void pci_set_enabled(PCIDevice *d, bool state)
 {
-    if (d->has_power == state) {
+    if (d->is_enabled == state) {
         return;
     }
 
-    d->has_power = state;
+    d->is_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->has_power);
-    if (!d->has_power) {
+                               & PCI_COMMAND_MASTER) && d->is_enabled);
+    if (!d->is_enabled) {
         pci_device_reset(d);
     }
 }
diff --git a/hw/pci/pci_host.c b/hw/pci/pci_host.c
index dfe6fe618401..d7e13d72ce07 100644
--- a/hw/pci/pci_host.c
+++ b/hw/pci/pci_host.c
@@ -86,7 +86,7 @@ void pci_host_config_write_common(PCIDevice *pci_dev, uint32_t addr,
      * allowing direct removal of unexposed functions.
      */
     if ((pci_dev->qdev.hotplugged && !pci_get_function_0(pci_dev)) ||
-        !pci_dev->has_power || is_pci_dev_ejected(pci_dev)) {
+        !pci_dev->is_enabled || is_pci_dev_ejected(pci_dev)) {
         return;
     }
 
@@ -111,7 +111,7 @@ uint32_t pci_host_config_read_common(PCIDevice *pci_dev, uint32_t addr,
      * allowing direct removal of unexposed functions.
      */
     if ((pci_dev->qdev.hotplugged && !pci_get_function_0(pci_dev)) ||
-        !pci_dev->has_power || is_pci_dev_ejected(pci_dev)) {
+        !pci_dev->is_enabled || is_pci_dev_ejected(pci_dev)) {
         return ~0x0;
     }
 
diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c
index 6db0cf69cd8a..f34c157e1fd3 100644
--- a/hw/pci/pcie.c
+++ b/hw/pci/pcie.c
@@ -394,7 +394,9 @@ static void pcie_set_power_device(PCIBus *bus, PCIDevice *dev, void *opaque)
 {
     bool *power = opaque;
 
-    pci_set_power(dev, *power);
+    if (!pci_is_vf(dev)) {
+        pci_set_enabled(dev, *power);
+    }
 }
 
 static void pcie_cap_update_power(PCIDevice *hotplug_dev)
diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c
index da209b7f47fd..9ba34cf8f8ed 100644
--- a/hw/pci/pcie_sriov.c
+++ b/hw/pci/pcie_sriov.c
@@ -20,15 +20,29 @@
 #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 void unrealize_vfs(PCIDevice *dev, uint16_t total_vfs)
+{
+    for (uint16_t i = 0; i < total_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: ");
+        }
+        object_unparent(OBJECT(vf));
+        object_unref(OBJECT(vf));
+    }
+    g_free(dev->exp.sriov_pf.vf);
+    dev->exp.sriov_pf.vf = NULL;
+}
 
-void pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
+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)
+                        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;
 
@@ -36,7 +50,6 @@ void pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
                         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 +82,35 @@ 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);
+
+    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)) {
+            unrealize_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;
+
+    unrealize_vfs(dev, pci_get_word(cfg + PCI_SRIOV_TOTAL_VF));
 }
 
 void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num,
@@ -141,38 +176,11 @@ void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num,
     }
 }
 
-static PCIDevice *register_vf(PCIDevice *pf, int devfn, const char *name,
-                              uint16_t vf_num)
-{
-    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;
-    }
-
-    /* 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);
-
-    return dev;
-}
-
 static void register_vfs(PCIDevice *dev)
 {
     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);
@@ -180,18 +188,10 @@ static void register_vfs(PCIDevice *dev)
         return;
     }
 
-    dev->exp.sriov_pf.vf = g_new(PCIDevice *, num_vfs);
-
     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;
-        }
-        devfn += vf_stride;
+        pci_set_enabled(dev->exp.sriov_pf.vf[i], true);
     }
     dev->exp.sriov_pf.num_vfs = num_vfs;
 }
@@ -204,16 +204,8 @@ static void unregister_vfs(PCIDevice *dev)
     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: ");
-        }
-        object_unparent(OBJECT(vf));
-        object_unref(OBJECT(vf));
+        pci_set_enabled(dev->exp.sriov_pf.vf[i], false);
     }
-    g_free(dev->exp.sriov_pf.vf);
-    dev->exp.sriov_pf.vf = NULL;
     dev->exp.sriov_pf.num_vfs = 0;
     pci_set_word(dev->config + dev->exp.sriov_cap + PCI_SRIOV_NUM_VF, 0);
 }

-- 
2.43.0

[PATCH 6/6] pcie_sriov: Release VFs failed to realize

[Akihiko Odaki]

Release VFs failed to realize just as we do in unregister_vfs().

Fixes: 7c0fa8dff811 ("pcie: Add support for Single Root I/O Virtualization (SR/IOV)")
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
---
 hw/pci/pcie_sriov.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c
index 9ba34cf8f8ed..9d668b8d6c17 100644
--- a/hw/pci/pcie_sriov.c
+++ b/hw/pci/pcie_sriov.c
@@ -91,6 +91,8 @@ bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
         vf->exp.sriov_vf.vf_number = i;
 
         if (!qdev_realize(&vf->qdev, bus, errp)) {
+            object_unparent(OBJECT(vf));
+            object_unref(vf);
             unrealize_vfs(dev, i);
             return false;
         }

-- 
2.43.0