Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6

torvalds · torvalds · commit 0c3bef612881 · 2011-08-19T10:02:37.000-07:00
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6:
  PCI: OF: Don't crash when bridge parent is NULL.
  PCI: export pcie_bus_configure_settings symbol
  PCI: code and comments cleanup
  PCI: make cardbus-bridge resources optional
  PCI: make SRIOV resources optional
  PCI : ability to relocate assigned pci-resources
  PCI: honor child buses add_size in hot plug configuration
  PCI: Set PCI-E Max Payload Size on fabric
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
@@ -360,6 +360,15 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
 		}
 	}
 
+	/* After the PCI-E bus has been walked and all devices discovered,
+	 * configure any settings of the fabric that might be necessary.
+	 */
+	if (bus) {
+		struct pci_bus *child;
+		list_for_each_entry(child, &bus->children, node)
+			pcie_bus_configure_settings(child, child->self->pcie_mpss);
+	}
+
 	if (!bus)
 		kfree(sd);
 
diff --git a/drivers/pci/hotplug/pcihp_slot.c b/drivers/pci/hotplug/pcihp_slot.c
@@ -158,47 +158,6 @@ static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp)
 	 */
 }
 
-/* Program PCIE MaxPayload setting on device: ensure parent maxpayload <= device */
-static int pci_set_payload(struct pci_dev *dev)
-{
-       int pos, ppos;
-       u16 pctl, psz;
-       u16 dctl, dsz, dcap, dmax;
-       struct pci_dev *parent;
-
-       parent = dev->bus->self;
-       pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
-       if (!pos)
-               return 0;
-
-       /* Read Device MaxPayload capability and setting */
-       pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &dctl);
-       pci_read_config_word(dev, pos + PCI_EXP_DEVCAP, &dcap);
-       dsz = (dctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5;
-       dmax = (dcap & PCI_EXP_DEVCAP_PAYLOAD);
-
-       /* Read Parent MaxPayload setting */
-       ppos = pci_find_capability(parent, PCI_CAP_ID_EXP);
-       if (!ppos)
-               return 0;
-       pci_read_config_word(parent, ppos + PCI_EXP_DEVCTL, &pctl);
-       psz = (pctl &  PCI_EXP_DEVCTL_PAYLOAD) >> 5;
-
-       /* If parent payload > device max payload -> error
-        * If parent payload > device payload -> set speed
-        * If parent payload <= device payload -> do nothing
-        */
-       if (psz > dmax)
-               return -1;
-       else if (psz > dsz) {
-               dev_info(&dev->dev, "Setting MaxPayload to %d\n", 128 << psz);
-               pci_write_config_word(dev, pos + PCI_EXP_DEVCTL,
-                                     (dctl & ~PCI_EXP_DEVCTL_PAYLOAD) +
-                                     (psz << 5));
-       }
-       return 0;
-}
-
 void pci_configure_slot(struct pci_dev *dev)
 {
 	struct pci_dev *cdev;
@@ -210,9 +169,7 @@ void pci_configure_slot(struct pci_dev *dev)
 			(dev->class >> 8) == PCI_CLASS_BRIDGE_PCI)))
 		return;
 
-       ret = pci_set_payload(dev);
-       if (ret)
-               dev_warn(&dev->dev, "could not set device max payload\n");
+	pcie_bus_configure_settings(dev->bus, dev->bus->self->pcie_mpss);
 
 	memset(&hpp, 0, sizeof(hpp));
 	ret = pci_get_hp_params(dev, &hpp);
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
@@ -55,7 +55,7 @@ struct device_node * __weak pcibios_get_phb_of_node(struct pci_bus *bus)
 	 */
 	if (bus->bridge->of_node)
 		return of_node_get(bus->bridge->of_node);
-	if (bus->bridge->parent->of_node)
+	if (bus->bridge->parent && bus->bridge->parent->of_node)
 		return of_node_get(bus->bridge->parent->of_node);
 	return NULL;
 }
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
@@ -77,6 +77,8 @@ unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE;
 unsigned long pci_hotplug_io_size  = DEFAULT_HOTPLUG_IO_SIZE;
 unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE;
 
+enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_PERFORMANCE;
+
 /*
  * The default CLS is used if arch didn't set CLS explicitly and not
  * all pci devices agree on the same value.  Arch can override either
@@ -3222,6 +3224,67 @@ int pcie_set_readrq(struct pci_dev *dev, int rq)
 }
 EXPORT_SYMBOL(pcie_set_readrq);
 
+/**
+ * pcie_get_mps - get PCI Express maximum payload size
+ * @dev: PCI device to query
+ *
+ * Returns maximum payload size in bytes
+ *    or appropriate error value.
+ */
+int pcie_get_mps(struct pci_dev *dev)
+{
+	int ret, cap;
+	u16 ctl;
+
+	cap = pci_pcie_cap(dev);
+	if (!cap)
+		return -EINVAL;
+
+	ret = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl);
+	if (!ret)
+		ret = 128 << ((ctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5);
+
+	return ret;
+}
+
+/**
+ * pcie_set_mps - set PCI Express maximum payload size
+ * @dev: PCI device to query
+ * @rq: maximum payload size in bytes
+ *    valid values are 128, 256, 512, 1024, 2048, 4096
+ *
+ * If possible sets maximum payload size
+ */
+int pcie_set_mps(struct pci_dev *dev, int mps)
+{
+	int cap, err = -EINVAL;
+	u16 ctl, v;
+
+	if (mps < 128 || mps > 4096 || !is_power_of_2(mps))
+		goto out;
+
+	v = ffs(mps) - 8;
+	if (v > dev->pcie_mpss) 
+		goto out;
+	v <<= 5;
+
+	cap = pci_pcie_cap(dev);
+	if (!cap)
+		goto out;
+
+	err = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl);
+	if (err)
+		goto out;
+
+	if ((ctl & PCI_EXP_DEVCTL_PAYLOAD) != v) {
+		ctl &= ~PCI_EXP_DEVCTL_PAYLOAD;
+		ctl |= v;
+		err = pci_write_config_word(dev, cap + PCI_EXP_DEVCTL, ctl);
+	}
+out:
+	return err;
+}
+
 /**
  * pci_select_bars - Make BAR mask from the type of resource
  * @dev: the PCI device for which BAR mask is made
@@ -3505,6 +3568,10 @@ static int __init pci_setup(char *str)
 				pci_hotplug_io_size = memparse(str + 9, &str);
 			} else if (!strncmp(str, "hpmemsize=", 10)) {
 				pci_hotplug_mem_size = memparse(str + 10, &str);
+			} else if (!strncmp(str, "pcie_bus_safe", 13)) {
+				pcie_bus_config = PCIE_BUS_SAFE;
+			} else if (!strncmp(str, "pcie_bus_perf", 13)) {
+				pcie_bus_config = PCIE_BUS_PERFORMANCE;
 			} else {
 				printk(KERN_ERR "PCI: Unknown option `%s'\n",
 						str);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
@@ -283,6 +283,8 @@ static inline int pci_iov_bus_range(struct pci_bus *bus)
 
 #endif /* CONFIG_PCI_IOV */
 
+extern unsigned long pci_cardbus_resource_alignment(struct resource *);
+
 static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
 					 struct resource *res)
 {
@@ -292,6 +294,8 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
 	if (resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END)
 		return pci_sriov_resource_alignment(dev, resno);
 #endif
+	if (dev->class >> 8  == PCI_CLASS_BRIDGE_CARDBUS)
+		return pci_cardbus_resource_alignment(res);
 	return resource_alignment(res);
 }
 
diff --git 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 +1328,150 @@ 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);
+}
+EXPORT_SYMBOL_GPL(pcie_bus_configure_settings);
+
 unsigned int __devinit pci_scan_child_bus(struct pci_bus *bus)
 {
 	unsigned int devfn, pass, max = bus->secondary;
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
diff --git a/include/linux/pci.h b/include/linux/pci.h

Original file line number	Diff line number	Diff line change
`@@ -360,6 +360,15 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)`
`360`	`360`	`}`
`361`	`361`	`}`
`362`	`362`
	`363`	`+ /* After the PCI-E bus has been walked and all devices discovered,`
	`364`	`+ * configure any settings of the fabric that might be necessary.`
	`365`	`+ */`
	`366`	`+ if (bus) {`
	`367`	`+ struct pci_bus *child;`
	`368`	`+ list_for_each_entry(child, &bus->children, node)`
	`369`	`+ pcie_bus_configure_settings(child, child->self->pcie_mpss);`
	`370`	`+ }`
	`371`	`+`
`363`	`372`	`if (!bus)`
`364`	`373`	`kfree(sd);`
`365`	`374`
Original file line number	Diff line number	Diff line change
`@@ -55,7 +55,7 @@ struct device_node * __weak pcibios_get_phb_of_node(struct pci_bus *bus)`
`55`	`55`	`*/`
`56`	`56`	`if (bus->bridge->of_node)`
`57`	`57`	`return of_node_get(bus->bridge->of_node);`
`58`		`- if (bus->bridge->parent->of_node)`
	`58`	`+ if (bus->bridge->parent && bus->bridge->parent->of_node)`
`59`	`59`	`return of_node_get(bus->bridge->parent->of_node);`
`60`	`60`	`return NULL;`
`61`	`61`	`}`
Original file line number	Diff line number	Diff line change
`@@ -283,6 +283,8 @@ static inline int pci_iov_bus_range(struct pci_bus *bus)`
`283`	`283`
`284`	`284`	`#endif /* CONFIG_PCI_IOV */`
`285`	`285`
	`286`	`+extern unsigned long pci_cardbus_resource_alignment(struct resource *);`
	`287`	`+`
`286`	`288`	`static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,`
`287`	`289`	`struct resource *res)`
`288`	`290`	`{`
`@@ -292,6 +294,8 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,`
`292`	`294`	`if (resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END)`
`293`	`295`	`return pci_sriov_resource_alignment(dev, resno);`
`294`	`296`	`#endif`
	`297`	`+ if (dev->class >> 8 == PCI_CLASS_BRIDGE_CARDBUS)`
	`298`	`+ return pci_cardbus_resource_alignment(res);`
`295`	`299`	`return resource_alignment(res);`
`296`	`300`	`}`
`297`	`301`