From 73aae596d106859e1e297ff9a106a8222721b4bd Mon Sep 17 00:00:00 2001 From: Myron Stowe Date: Mon, 13 Aug 2018 12:19:39 -0600 Subject: [PATCH] PCI: Skip MPS logic for Virtual Functions (VFs) commit 3dbe97efe8bf450b183d6dee2305cbc032e6b8a4 upstream. PCIe r4.0, sec 9.3.5.4, "Device Control Register", shows both Max_Payload_Size (MPS) and Max_Read_request_Size (MRRS) to be 'RsvdP' for VFs. Just prior to the table it states: "PF and VF functionality is defined in Section 7.5.3.4 except where noted in Table 9-16. For VF fields marked 'RsvdP', the PF setting applies to the VF." All of which implies that with respect to Max_Payload_Size Supported (MPSS), MPS, and MRRS values, we should not be paying any attention to the VF's fields, but rather only to the PF's. Only looking at the PF's fields also logically makes sense as it's the sole physical interface to the PCIe bus. Link: https://bugzilla.kernel.org/show_bug.cgi?id=200527 Fixes: 27d868b5e6cf ("PCI: Set MPS to match upstream bridge") Signed-off-by: Myron Stowe Signed-off-by: Bjorn Helgaas Cc: stable@vger.kernel.org # 4.3+ Cc: Keith Busch Cc: Sinan Kaya Cc: Dongdong Liu Cc: Jon Mason Signed-off-by: Greg Kroah-Hartman --- drivers/pci/probe.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 56340abe4fc6..16611cf3aba4 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1363,6 +1363,10 @@ static void pci_configure_mps(struct pci_dev *dev) if (!pci_is_pcie(dev) || !bridge || !pci_is_pcie(bridge)) return; + /* MPS and MRRS fields are of type 'RsvdP' for VFs, short-circuit out */ + if (dev->is_virtfn) + return; + mps = pcie_get_mps(dev); p_mps = pcie_get_mps(bridge); -- 2.20.1