[PULL v2 84/88] pcie_sriov: Reuse SR-IOV VF device instances

[Michael S. Tsirkin]

From: Akihiko Odaki <akihiko.odaki@daynix.com>

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>
Message-Id: <20240627-reuse-v10-6-7ca0b8ed3d9f@daynix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/hw/pci/pci.h        |  5 --
 include/hw/pci/pci_device.h | 15 ++++++
 include/hw/pci/pcie_sriov.h |  1 -
 hw/pci/pci.c                |  2 +-
 hw/pci/pcie_sriov.c         | 95 ++++++++++++++++---------------------
 5 files changed, 56 insertions(+), 62 deletions(-)

diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index fe04b4fafd..14a869eeaa 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -680,9 +680,4 @@ static inline void pci_irq_pulse(PCIDevice *pci_dev)
 MSIMessage pci_get_msi_message(PCIDevice *dev, int vector);
 void pci_set_enabled(PCIDevice *pci_dev, bool state);
 
-static inline void pci_set_power(PCIDevice *pci_dev, bool state)
-{
-    pci_set_enabled(pci_dev, state);
-}
-
 #endif
diff --git a/include/hw/pci/pci_device.h b/include/hw/pci/pci_device.h
index d57f9ce838..ca15132508 100644
--- a/include/hw/pci/pci_device.h
+++ b/include/hw/pci/pci_device.h
@@ -205,6 +205,21 @@ static inline uint16_t pci_get_bdf(PCIDevice *dev)
     return PCI_BUILD_BDF(pci_bus_num(pci_get_bus(dev)), dev->devfn);
 }
 
+static inline void pci_set_power(PCIDevice *pci_dev, bool state)
+{
+    /*
+     * Don't change the enabled state of VFs when powering on/off the device.
+     *
+     * When powering on, VFs must not be enabled immediately but they must
+     * wait until the guest configures SR-IOV.
+     * When powering off, their corresponding PFs will be reset and disable
+     * VFs.
+     */
+    if (!pci_is_vf(pci_dev)) {
+        pci_set_enabled(pci_dev, state);
+    }
+}
+
 uint16_t pci_requester_id(PCIDevice *dev);
 
 /* DMA access functions */
diff --git a/include/hw/pci/pcie_sriov.h b/include/hw/pci/pcie_sriov.h
index aa704e8f9d..70649236c1 100644
--- a/include/hw/pci/pcie_sriov.h
+++ b/include/hw/pci/pcie_sriov.h
@@ -18,7 +18,6 @@
 typedef 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 */
 } PCIESriovPF;
 
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index 68d30feb86..e32a69f3fa 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -2895,7 +2895,7 @@ void pci_set_enabled(PCIDevice *d, bool state)
     memory_region_set_enabled(&d->bus_master_enable_region,
                               (pci_get_word(d->config + PCI_COMMAND)
                                & PCI_COMMAND_MASTER) && d->enabled);
-    if (!d->enabled) {
+    if (d->qdev.realized) {
         pci_device_reset(d);
     }
 }
diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c
index f0bde0d3fc..faadb0d2ea 100644
--- a/hw/pci/pcie_sriov.c
+++ b/hw/pci/pcie_sriov.c
@@ -20,9 +20,16 @@
 #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 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;
+}
 
 bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
                         const char *vfname, uint16_t vf_dev_id,
@@ -30,6 +37,8 @@ bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
                         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;
 
@@ -49,7 +58,6 @@ bool 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);
@@ -83,14 +91,34 @@ bool pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset,
 
     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)) {
+            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;
+
+    unparent_vfs(dev, pci_get_word(cfg + PCI_SRIOV_TOTAL_VF));
 }
 
 void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num,
@@ -156,38 +184,11 @@ 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);
@@ -195,18 +196,10 @@ 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;
 }
@@ -219,12 +212,8 @@ 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++) {
-        PCIDevice *vf = dev->exp.sriov_pf.vf[i];
-        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;
 }
 
@@ -246,14 +235,10 @@ 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);
         }
     }
 }
-- 
MST