summaryrefslogtreecommitdiffstats
path: root/drivers/pci/probe.c
diff options
context:
space:
mode:
authorJon Mason <mason@myri.com>2011-07-20 15:20:54 -0500
committerJesse Barnes <jbarnes@virtuousgeek.org>2011-08-01 11:49:16 -0700
commitb03e7495a862b028294f59fc87286d6d78ee7fa1 (patch)
tree836fbfc2b0e34f034cb273c4d065baba3a65178c /drivers/pci/probe.c
parent5f66d2b58ca879e70740c82422354144845d6dd3 (diff)
PCI: Set PCI-E Max Payload Size on fabric
On a given PCI-E fabric, each device, bridge, and root port can have a different PCI-E maximum payload size. There is a sizable performance boost for having the largest possible maximum payload size on each PCI-E device. However, if improperly configured, fatal bus errors can occur. Thus, it is important to ensure that PCI-E payloads sends by a device are never larger than the MPS setting of all devices on the way to the destination. This can be achieved two ways: - A conservative approach is to use the smallest common denominator of the entire tree below a root complex for every device on that fabric. This means for example that having a 128 bytes MPS USB controller on one leg of a switch will dramatically reduce performances of a video card or 10GE adapter on another leg of that same switch. It also means that any hierarchy supporting hotplug slots (including expresscard or thunderbolt I suppose, dbl check that) will have to be entirely clamped to 128 bytes since we cannot predict what will be plugged into those slots, and we cannot change the MPS on a "live" system. - A more optimal way is possible, if it falls within a couple of constraints: * The top-level host bridge will never generate packets larger than the smallest TLP (or if it can be controlled independently from its MPS at least) * The device will never generate packets larger than MPS (which can be configured via MRRS) * No support of direct PCI-E <-> PCI-E transfers between devices without some additional code to specifically deal with that case Then we can use an approach that basically ignores downstream requests and focuses exclusively on upstream requests. In that case, all we need to care about is that a device MPS is no larger than its parent MPS, which allows us to keep all switches/bridges to the max MPS supported by their parent and eventually the PHB. In this case, your USB controller would no longer "starve" your 10GE Ethernet and your hotplug slots won't affect your global MPS. Additionally, the hotplugged devices themselves can be configured to a larger MPS up to the value configured in the hotplug bridge. To choose between the two available options, two PCI kernel boot args have been added to the PCI calls. "pcie_bus_safe" will provide the former behavior, while "pcie_bus_perf" will perform the latter behavior. By default, the latter behavior is used. NOTE: due to the location of the enablement, each arch will need to add calls to this function. This patch only enables x86. This patch includes a number of changes recommended by Benjamin Herrenschmidt. Tested-by: Jordan_Hargrave@dell.com Signed-off-by: Jon Mason <mason@myri.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Diffstat (limited to 'drivers/pci/probe.c')
-rw-r--r--drivers/pci/probe.c145
1 files changed, 145 insertions, 0 deletions
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 795c9026d55..5becf7cd50d 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -856,6 +856,8 @@ void set_pcie_port_type(struct pci_dev *pdev)
pdev->pcie_cap = pos;
pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, &reg16);
pdev->pcie_type = (reg16 & PCI_EXP_FLAGS_TYPE) >> 4;
+ pci_read_config_word(pdev, pos + PCI_EXP_DEVCAP, &reg16);
+ pdev->pcie_mpss = reg16 & PCI_EXP_DEVCAP_PAYLOAD;
}
void set_pcie_hotplug_bridge(struct pci_dev *pdev)
@@ -1326,6 +1328,149 @@ int pci_scan_slot(struct pci_bus *bus, int devfn)
return nr;
}
+static int pcie_find_smpss(struct pci_dev *dev, void *data)
+{
+ u8 *smpss = data;
+
+ if (!pci_is_pcie(dev))
+ return 0;
+
+ /* For PCIE hotplug enabled slots not connected directly to a
+ * PCI-E root port, there can be problems when hotplugging
+ * devices. This is due to the possibility of hotplugging a
+ * device into the fabric with a smaller MPS that the devices
+ * currently running have configured. Modifying the MPS on the
+ * running devices could cause a fatal bus error due to an
+ * incoming frame being larger than the newly configured MPS.
+ * To work around this, the MPS for the entire fabric must be
+ * set to the minimum size. Any devices hotplugged into this
+ * fabric will have the minimum MPS set. If the PCI hotplug
+ * slot is directly connected to the root port and there are not
+ * other devices on the fabric (which seems to be the most
+ * common case), then this is not an issue and MPS discovery
+ * will occur as normal.
+ */
+ if (dev->is_hotplug_bridge && (!list_is_singular(&dev->bus->devices) ||
+ dev->bus->self->pcie_type != PCI_EXP_TYPE_ROOT_PORT))
+ *smpss = 0;
+
+ if (*smpss > dev->pcie_mpss)
+ *smpss = dev->pcie_mpss;
+
+ return 0;
+}
+
+static void pcie_write_mps(struct pci_dev *dev, int mps)
+{
+ int rc, dev_mpss;
+
+ dev_mpss = 128 << dev->pcie_mpss;
+
+ if (pcie_bus_config == PCIE_BUS_PERFORMANCE) {
+ if (dev->bus->self) {
+ dev_dbg(&dev->bus->dev, "Bus MPSS %d\n",
+ 128 << dev->bus->self->pcie_mpss);
+
+ /* For "MPS Force Max", the assumption is made that
+ * downstream communication will never be larger than
+ * the MRRS. So, the MPS only needs to be configured
+ * for the upstream communication. This being the case,
+ * walk from the top down and set the MPS of the child
+ * to that of the parent bus.
+ */
+ mps = 128 << dev->bus->self->pcie_mpss;
+ if (mps > dev_mpss)
+ dev_warn(&dev->dev, "MPS configured higher than"
+ " maximum supported by the device. If"
+ " a bus issue occurs, try running with"
+ " pci=pcie_bus_safe.\n");
+ }
+
+ dev->pcie_mpss = ffs(mps) - 8;
+ }
+
+ rc = pcie_set_mps(dev, mps);
+ if (rc)
+ dev_err(&dev->dev, "Failed attempting to set the MPS\n");
+}
+
+static void pcie_write_mrrs(struct pci_dev *dev, int mps)
+{
+ int rc, mrrs;
+
+ if (pcie_bus_config == PCIE_BUS_PERFORMANCE) {
+ int dev_mpss = 128 << dev->pcie_mpss;
+
+ /* For Max performance, the MRRS must be set to the largest
+ * supported value. However, it cannot be configured larger
+ * than the MPS the device or the bus can support. This assumes
+ * that the largest MRRS available on the device cannot be
+ * smaller than the device MPSS.
+ */
+ mrrs = mps < dev_mpss ? mps : dev_mpss;
+ } else
+ /* In the "safe" case, configure the MRRS for fairness on the
+ * bus by making all devices have the same size
+ */
+ mrrs = mps;
+
+
+ /* MRRS is a R/W register. Invalid values can be written, but a
+ * subsiquent read will verify if the value is acceptable or not.
+ * If the MRRS value provided is not acceptable (e.g., too large),
+ * shrink the value until it is acceptable to the HW.
+ */
+ while (mrrs != pcie_get_readrq(dev) && mrrs >= 128) {
+ rc = pcie_set_readrq(dev, mrrs);
+ if (rc)
+ dev_err(&dev->dev, "Failed attempting to set the MRRS\n");
+
+ mrrs /= 2;
+ }
+}
+
+static int pcie_bus_configure_set(struct pci_dev *dev, void *data)
+{
+ int mps = 128 << *(u8 *)data;
+
+ if (!pci_is_pcie(dev))
+ return 0;
+
+ dev_info(&dev->dev, "Dev MPS %d MPSS %d MRRS %d\n",
+ pcie_get_mps(dev), 128<<dev->pcie_mpss, pcie_get_readrq(dev));
+
+ pcie_write_mps(dev, mps);
+ pcie_write_mrrs(dev, mps);
+
+ dev_info(&dev->dev, "Dev MPS %d MPSS %d MRRS %d\n",
+ pcie_get_mps(dev), 128<<dev->pcie_mpss, pcie_get_readrq(dev));
+
+ return 0;
+}
+
+/* pcie_bus_configure_mps requires that pci_walk_bus work in a top-down,
+ * parents then children fashion. If this changes, then this code will not
+ * work as designed.
+ */
+void pcie_bus_configure_settings(struct pci_bus *bus, u8 mpss)
+{
+ u8 smpss = mpss;
+
+ if (!bus->self)
+ return;
+
+ if (!pci_is_pcie(bus->self))
+ return;
+
+ if (pcie_bus_config == PCIE_BUS_SAFE) {
+ pcie_find_smpss(bus->self, &smpss);
+ pci_walk_bus(bus, pcie_find_smpss, &smpss);
+ }
+
+ pcie_bus_configure_set(bus->self, &smpss);
+ pci_walk_bus(bus, pcie_bus_configure_set, &smpss);
+}
+
unsigned int __devinit pci_scan_child_bus(struct pci_bus *bus)
{
unsigned int devfn, pass, max = bus->secondary;