7 files changed, 52 insertions, 50 deletions

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index f46914a0f33e..d35ec34de1b4 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1672,12 +1672,8 @@ void pcibios_scan_phb(struct pci_controller *hose)
         /* Configure PCI Express settings */
         if (bus && !pci_has_flag(PCI_PROBE_ONLY)) {
                 struct pci_bus *child;
-                list_for_each_entry(child, &bus->children, node) {
-                        struct pci_dev *self = child->self;
-                        if (!self)
-                                continue;
-                        pcie_bus_configure_settings(child, self->pcie_mpss);
-                }
+                list_for_each_entry(child, &bus->children, node)
+                        pcie_bus_configure_settings(child);
         }
 }
 
diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c
index 11425633b2d7..6640e7bbeaa2 100644
--- a/arch/tile/kernel/pci_gx.c
+++ b/arch/tile/kernel/pci_gx.c
@@ -508,13 +508,8 @@ static void fixup_read_and_payload_sizes(struct pci_controller *controller)
                                                 rc_dev_cap.word);
 
         /* Configure PCI Express MPS setting. */
-        list_for_each_entry(child, &root_bus->children, node) {
-                struct pci_dev *self = child->self;
-                if (!self)
-                        continue;
-
-                pcie_bus_configure_settings(child, self->pcie_mpss);
-        }
+        list_for_each_entry(child, &root_bus->children, node)
+                pcie_bus_configure_settings(child);
 
         /*
          * Set the mac_config register in trio based on the MPS/MRS of the link.
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index d641897a1f4e..b30e937689d6 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -568,13 +568,8 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
          */
         if (bus) {
                 struct pci_bus *child;
-                list_for_each_entry(child, &bus->children, node) {
-                        struct pci_dev *self = child->self;
-                        if (!self)
-                                continue;
-
-                        pcie_bus_configure_settings(child, self->pcie_mpss);
-                }
+                list_for_each_entry(child, &bus->children, node)
+                        pcie_bus_configure_settings(child);
         }
 
         if (bus && node != -1) {
diff --git a/drivers/pci/hotplug/pcihp_slot.c b/drivers/pci/hotplug/pcihp_slot.c
index fec2d5b75440..16f920352317 100644
--- a/drivers/pci/hotplug/pcihp_slot.c
+++ b/drivers/pci/hotplug/pcihp_slot.c
@@ -160,9 +160,8 @@ void pci_configure_slot(struct pci_dev *dev)
                         (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI)))
                 return;
 
-        if (dev->bus && dev->bus->self)
-                pcie_bus_configure_settings(dev->bus,
-                                            dev->bus->self->pcie_mpss);
+        if (dev->bus)
+                pcie_bus_configure_settings(dev->bus);
 
         memset(&hpp, 0, sizeof(hpp));
         ret = pci_get_hp_params(dev, &hpp);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index d3fdce8f3d65..4e15bc9712fd 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3939,8 +3939,6 @@ int pcie_set_readrq(struct pci_dev *dev, int rq)
         if (pcie_bus_config == PCIE_BUS_PERFORMANCE) {
                 int mps = pcie_get_mps(dev);
 
-                if (mps < 0)
-                        return mps;
                 if (mps < rq)
                         rq = mps;
         }
@@ -3957,7 +3955,6 @@ EXPORT_SYMBOL(pcie_set_readrq);
  * @dev: PCI device to query
  *
  * Returns maximum payload size in bytes
- *    or appropriate error value.
  */
 int pcie_get_mps(struct pci_dev *dev)
 {
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 4ab388a6cc26..a57762fbe10e 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1491,24 +1491,23 @@ static int pcie_find_smpss(struct pci_dev *dev, void *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.
+        /*
+         * We don't have a way to change MPS settings on devices that have
+         * drivers attached.  A hot-added device might support only the minimum
+         * MPS setting (MPS=128).  Therefore, if the fabric contains a bridge
+         * where devices may be hot-added, we limit the fabric MPS to 128 so
+         * hot-added devices will work correctly.
+         *
+         * However, if we hot-add a device to a slot directly below a Root
+         * Port, it's impossible for there to be other existing devices below
+         * the port.  We don't limit the MPS in this case because we can
+         * reconfigure MPS on both the Root Port and the hot-added device,
+         * and there are no other devices involved.
+         *
+         * Note that this PCIE_BUS_SAFE path assumes no peer-to-peer DMA.
          */
-        if (dev->is_hotplug_bridge && (!list_is_singular(&dev->bus->devices) ||
-             (dev->bus->self &&
-              pci_pcie_type(dev->bus->self) != PCI_EXP_TYPE_ROOT_PORT)))
+        if (dev->is_hotplug_bridge &&
+            pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT)
                 *smpss = 0;
 
         if (*smpss > dev->pcie_mpss)
@@ -1583,6 +1582,22 @@ static void pcie_write_mrrs(struct pci_dev *dev)
                         "with pci=pcie_bus_safe.\n");
 }
 
+static void pcie_bus_detect_mps(struct pci_dev *dev)
+{
+        struct pci_dev *bridge = dev->bus->self;
+        int mps, p_mps;
+
+        if (!bridge)
+                return;
+
+        mps = pcie_get_mps(dev);
+        p_mps = pcie_get_mps(bridge);
+
+        if (mps != p_mps)
+                dev_warn(&dev->dev, "Max Payload Size %d, but upstream %s set to %d; if necessary, use \"pci=pcie_bus_safe\" and report a bug\n",
+                         mps, pci_name(bridge), p_mps);
+}
+
 static int pcie_bus_configure_set(struct pci_dev *dev, void *data)
 {
         int mps, orig_mps;
@@ -1590,13 +1605,18 @@ static int pcie_bus_configure_set(struct pci_dev *dev, void *data)
         if (!pci_is_pcie(dev))
                 return 0;
 
+        if (pcie_bus_config == PCIE_BUS_TUNE_OFF) {
+                pcie_bus_detect_mps(dev);
+                return 0;
+        }
+
         mps = 128 << *(u8 *)data;
         orig_mps = pcie_get_mps(dev);
 
         pcie_write_mps(dev, mps);
         pcie_write_mrrs(dev);
 
-        dev_info(&dev->dev, "PCI-E Max Payload Size set to %4d/%4d (was %4d), "
+        dev_info(&dev->dev, "Max Payload Size set to %4d/%4d (was %4d), "
                  "Max Read Rq %4d\n", pcie_get_mps(dev), 128 << dev->pcie_mpss,
                  orig_mps, pcie_get_readrq(dev));
 
@@ -1607,25 +1627,25 @@ static int pcie_bus_configure_set(struct pci_dev *dev, void *data)
  * 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)
+void pcie_bus_configure_settings(struct pci_bus *bus)
 {
         u8 smpss;
 
-        if (!pci_is_pcie(bus->self))
+        if (!bus->self)
                 return;
 
-        if (pcie_bus_config == PCIE_BUS_TUNE_OFF)
+        if (!pci_is_pcie(bus->self))
                 return;
 
         /* FIXME - Peer to peer DMA is possible, though the endpoint would need
-         * to be aware to the MPS of the destination.  To work around this,
+         * to be aware of the MPS of the destination.  To work around this,
          * simply force the MPS of the entire system to the smallest possible.
          */
         if (pcie_bus_config == PCIE_BUS_PEER2PEER)
                 smpss = 0;
 
         if (pcie_bus_config == PCIE_BUS_SAFE) {
-                smpss = mpss;
+                smpss = bus->self->pcie_mpss;
 
                 pcie_find_smpss(bus->self, &smpss);
                 pci_walk_bus(bus, pcie_find_smpss, &smpss);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 82d1c78d3d91..b3b716524be5 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -675,7 +675,7 @@ struct pci_driver {
 /* these external functions are only available when PCI support is enabled */
 #ifdef CONFIG_PCI
 
-void pcie_bus_configure_settings(struct pci_bus *bus, u8 smpss);
+void pcie_bus_configure_settings(struct pci_bus *bus);
 
 enum pcie_bus_config_types {
         PCIE_BUS_TUNE_OFF,