From 502b50e87038e63011dbe83f210292b1c505b6c9 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 2 Oct 2017 12:39:10 -0600 Subject: [PATCH] vfio/pci: Virtualize Maximum Read Request Size commit cf0d53ba4947aad6e471491d5b20a567cbe92e56 upstream. MRRS defines the maximum read request size a device is allowed to make. Drivers will often increase this to allow more data transfer with a single request. Completions to this request are bound by the MPS setting for the bus. Aside from device quirks (none known), it doesn't seem to make sense to set an MRRS value less than MPS, yet this is a likely scenario given that user drivers do not have a system-wide view of the PCI topology. Virtualize MRRS such that the user can set MRRS >= MPS, but use MPS as the floor value that we'll write to hardware. Signed-off-by: Alex Williamson Signed-off-by: Greg Kroah-Hartman --- drivers/vfio/pci/vfio_pci_config.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 9f1ec4392209..7b8a957b008d 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -810,6 +810,7 @@ static int vfio_exp_config_write(struct vfio_pci_device *vdev, int pos, { __le16 *ctrl = (__le16 *)(vdev->vconfig + pos - offset + PCI_EXP_DEVCTL); + int readrq = le16_to_cpu(*ctrl) & PCI_EXP_DEVCTL_READRQ; count = vfio_default_config_write(vdev, pos, count, perm, offset, val); if (count < 0) @@ -835,6 +836,27 @@ static int vfio_exp_config_write(struct vfio_pci_device *vdev, int pos, pci_try_reset_function(vdev->pdev); } + /* + * MPS is virtualized to the user, writes do not change the physical + * register since determining a proper MPS value requires a system wide + * device view. The MRRS is largely independent of MPS, but since the + * user does not have that system-wide view, they might set a safe, but + * inefficiently low value. Here we allow writes through to hardware, + * but we set the floor to the physical device MPS setting, so that + * we can at least use full TLPs, as defined by the MPS value. + * + * NB, if any devices actually depend on an artificially low MRRS + * setting, this will need to be revisited, perhaps with a quirk + * though pcie_set_readrq(). + */ + if (readrq != (le16_to_cpu(*ctrl) & PCI_EXP_DEVCTL_READRQ)) { + readrq = 128 << + ((le16_to_cpu(*ctrl) & PCI_EXP_DEVCTL_READRQ) >> 12); + readrq = max(readrq, pcie_get_mps(vdev->pdev)); + + pcie_set_readrq(vdev->pdev, readrq); + } + return count; } @@ -853,11 +875,12 @@ static int __init init_pci_cap_exp_perm(struct perm_bits *perm) * Allow writes to device control fields, except devctl_phantom, * which could confuse IOMMU, MPS, which can break communication * with other physical devices, and the ARI bit in devctl2, which - * is set at probe time. FLR gets virtualized via our writefn. + * is set at probe time. FLR and MRRS get virtualized via our + * writefn. */ p_setw(perm, PCI_EXP_DEVCTL, - PCI_EXP_DEVCTL_BCR_FLR | PCI_EXP_DEVCTL_PAYLOAD, - ~PCI_EXP_DEVCTL_PHANTOM); + PCI_EXP_DEVCTL_BCR_FLR | PCI_EXP_DEVCTL_PAYLOAD | + PCI_EXP_DEVCTL_READRQ, ~PCI_EXP_DEVCTL_PHANTOM); p_setw(perm, PCI_EXP_DEVCTL2, NO_VIRT, ~PCI_EXP_DEVCTL2_ARI); return 0; } -- 2.20.1