[PULL v3 80/85] pcie_sriov: Ensure VF function number does not overflow

[Michael S. Tsirkin]

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

pci_new() aborts when creating a VF with a function number equals to or
is greater than PCI_DEVFN_MAX.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Message-Id: <20240627-reuse-v10-5-7ca0b8ed3d9f@daynix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 docs/pcie_sriov.txt         |  8 +++++---
 include/hw/pci/pcie_sriov.h |  5 +++--
 hw/net/igb.c                | 13 ++++++++++---
 hw/nvme/ctrl.c              | 24 ++++++++++++++++--------
 hw/pci/pcie_sriov.c         | 19 +++++++++++++++++--
 5 files changed, 51 insertions(+), 18 deletions(-)

diff --git a/docs/pcie_sriov.txt b/docs/pcie_sriov.txt
index a47aad0bfa..ab2142807f 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/pcie_sriov.h b/include/hw/pci/pcie_sriov.h
index 450cbef6c2..aa704e8f9d 100644
--- a/include/hw/pci/pcie_sriov.h
+++ b/include/hw/pci/pcie_sriov.h
@@ -27,10 +27,11 @@ typedef struct PCIESriovVF {
     uint16_t vf_number; /* Logical VF number of this function */
 } PCIESriovVF;
 
-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 b92bba402e..b6ca2f1b8a 100644
--- a/hw/net/igb.c
+++ b/hw/net/igb.c
@@ -446,9 +446,16 @@ 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 127c3d2383..066389e391 100644
--- a/hw/nvme/ctrl.c
+++ b/hw/nvme/ctrl.c
@@ -8048,7 +8048,8 @@ out:
     return pow2ceil(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;
@@ -8057,12 +8058,17 @@ 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)
@@ -8155,6 +8161,12 @@ 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) {
@@ -8165,10 +8177,6 @@ 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;
 }
 
diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c
index 499becd527..f0bde0d3fc 100644
--- a/hw/pci/pcie_sriov.c
+++ b/hw/pci/pcie_sriov.c
@@ -24,14 +24,27 @@ static PCIDevice *register_vf(PCIDevice *pf, int devfn,
                               const char *name, uint16_t vf_num);
 static void unregister_vfs(PCIDevice *dev);
 
-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)
 {
     uint8_t *cfg = dev->config + offset;
     uint8_t *wmask;
 
+    if (total_vfs) {
+        uint16_t ari_cap = pcie_find_capability(dev, PCI_EXT_CAP_ID_ARI);
+        uint16_t first_vf_devfn = dev->devfn + vf_offset;
+        uint16_t last_vf_devfn = first_vf_devfn + vf_stride * (total_vfs - 1);
+
+        if ((!ari_cap && PCI_SLOT(dev->devfn) != PCI_SLOT(last_vf_devfn)) ||
+            last_vf_devfn >= PCI_DEVFN_MAX) {
+            error_setg(errp, "VF function number overflows");
+            return false;
+        }
+    }
+
     pcie_add_capability(dev, PCI_EXT_CAP_ID_SRIOV, 1,
                         offset, PCI_EXT_CAP_SRIOV_SIZEOF);
     dev->exp.sriov_cap = offset;
@@ -69,6 +82,8 @@ 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;
 }
 
 void pcie_sriov_pf_exit(PCIDevice *dev)
-- 
MST