Commit 35b1de5 ("rdma/cxgb4: Fixes cxgb4 probe failure in VM when PF is exposed
through PCI Passthrough") introduced a regression, where VF failed to
initialize for Physical function 0 to Physical Function 3. In the above
commit, we removed the code which used to enable sriov for PF0 to PF3. Now
adding it back to get sriov working.
V2:
Removed SRIOV loop for PF[0..3] to instantiate the VF's as per David Miller's
comment
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
/* We control everything through one PF */
func = SOURCEPF_GET(readl(adapter->regs + PL_WHOAMI));
- if ((pdev->device == 0xa000 && func != 0) ||
- func != ent->driver_data) {
+ if (func != ent->driver_data) {
pci_save_state(pdev); /* to restore SR-IOV later */
- err = 0;
- goto out_unmap_bar0;
+ goto sriov;
}
adapter->pdev = pdev;
if (is_offload(adapter))
attach_ulds(adapter);
+sriov:
#ifdef CONFIG_PCI_IOV
if (func < ARRAY_SIZE(num_vf) && num_vf[func] > 0)
if (pci_enable_sriov(pdev, num_vf[func]) == 0)