1 files changed, 125 insertions, 70 deletions

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 70f10fa3c1b2..eeb50bd62402 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -96,7 +96,7 @@ static void release_pcibus_dev(struct device *dev)
 static struct class pcibus_class = {
 	.name		= "pci_bus",
 	.dev_release	= &release_pcibus_dev,
-	.dev_attrs	= pcibus_dev_attrs,
+	.dev_groups	= pcibus_groups,
 };
 
 static int __init pcibus_class_init(void)
@@ -156,6 +156,8 @@ static inline unsigned long decode_bar(struct pci_dev *dev, u32 bar)
 	return flags;
 }
 
+#define PCI_COMMAND_DECODE_ENABLE	(PCI_COMMAND_MEMORY | PCI_COMMAND_IO)
+
 /**
  * pci_read_base - read a PCI BAR
  * @dev: the PCI device
@@ -170,7 +172,7 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 {
 	u32 l, sz, mask;
 	u16 orig_cmd;
-	struct pci_bus_region region;
+	struct pci_bus_region region, inverted_region;
 	bool bar_too_big = false, bar_disabled = false;
 
 	mask = type ? PCI_ROM_ADDRESS_MASK : ~0;
@@ -178,8 +180,10 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 	/* No printks while decoding is disabled! */
 	if (!dev->mmio_always_on) {
 		pci_read_config_word(dev, PCI_COMMAND, &orig_cmd);
-		pci_write_config_word(dev, PCI_COMMAND,
-			orig_cmd & ~(PCI_COMMAND_MEMORY | PCI_COMMAND_IO));
+		if (orig_cmd & PCI_COMMAND_DECODE_ENABLE) {
+			pci_write_config_word(dev, PCI_COMMAND,
+				orig_cmd & ~PCI_COMMAND_DECODE_ENABLE);
+		}
 	}
 
 	res->name = pci_name(dev);
@@ -250,12 +254,10 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 			pci_write_config_dword(dev, pos + 4, 0);
 			region.start = 0;
 			region.end = sz64;
-			pcibios_bus_to_resource(dev, res, &region);
 			bar_disabled = true;
 		} else {
 			region.start = l64;
 			region.end = l64 + sz64;
-			pcibios_bus_to_resource(dev, res, &region);
 		}
 	} else {
 		sz = pci_size(l, sz, mask);
@@ -265,7 +267,28 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 
 		region.start = l;
 		region.end = l + sz;
-		pcibios_bus_to_resource(dev, res, &region);
+	}
+
+	pcibios_bus_to_resource(dev, res, &region);
+	pcibios_resource_to_bus(dev, &inverted_region, res);
+
+	/*
+	 * If "A" is a BAR value (a bus address), "bus_to_resource(A)" is
+	 * the corresponding resource address (the physical address used by
+	 * the CPU.  Converting that resource address back to a bus address
+	 * should yield the original BAR value:
+	 *
+	 *     resource_to_bus(bus_to_resource(A)) == A
+	 *
+	 * If it doesn't, CPU accesses to "bus_to_resource(A)" will not
+	 * be claimed by the device.
+	 */
+	if (inverted_region.start != region.start) {
+		dev_info(&dev->dev, "reg 0x%x: initial BAR value %pa invalid; forcing reassignment\n",
+			 pos, &region.start);
+		res->flags |= IORESOURCE_UNSET;
+		res->end -= res->start;
+		res->start = 0;
 	}
 
 	goto out;
@@ -274,13 +297,14 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 fail:
 	res->flags = 0;
 out:
-	if (!dev->mmio_always_on)
+	if (!dev->mmio_always_on &&
+	    (orig_cmd & PCI_COMMAND_DECODE_ENABLE))
 		pci_write_config_word(dev, PCI_COMMAND, orig_cmd);
 
 	if (bar_too_big)
-		dev_err(&dev->dev, "reg %x: can't handle 64-bit BAR\n", pos);
+		dev_err(&dev->dev, "reg 0x%x: can't handle 64-bit BAR\n", pos);
 	if (res->flags && !bar_disabled)
-		dev_printk(KERN_DEBUG, &dev->dev, "reg %x: %pR\n", pos, res);
+		dev_printk(KERN_DEBUG, &dev->dev, "reg 0x%x: %pR\n", pos, res);
 
 	return (res->flags & IORESOURCE_MEM_64) ? 1 : 0;
 }
@@ -451,33 +475,46 @@ void pci_read_bridge_bases(struct pci_bus *child)
 	}
 }
 
-static struct pci_bus * pci_alloc_bus(void)
+static struct pci_bus *pci_alloc_bus(void)
 {
 	struct pci_bus *b;
 
 	b = kzalloc(sizeof(*b), GFP_KERNEL);
-	if (b) {
-		INIT_LIST_HEAD(&b->node);
-		INIT_LIST_HEAD(&b->children);
-		INIT_LIST_HEAD(&b->devices);
-		INIT_LIST_HEAD(&b->slots);
-		INIT_LIST_HEAD(&b->resources);
-		b->max_bus_speed = PCI_SPEED_UNKNOWN;
-		b->cur_bus_speed = PCI_SPEED_UNKNOWN;
-	}
+	if (!b)
+		return NULL;
+
+	INIT_LIST_HEAD(&b->node);
+	INIT_LIST_HEAD(&b->children);
+	INIT_LIST_HEAD(&b->devices);
+	INIT_LIST_HEAD(&b->slots);
+	INIT_LIST_HEAD(&b->resources);
+	b->max_bus_speed = PCI_SPEED_UNKNOWN;
+	b->cur_bus_speed = PCI_SPEED_UNKNOWN;
 	return b;
 }
 
+static void pci_release_host_bridge_dev(struct device *dev)
+{
+	struct pci_host_bridge *bridge = to_pci_host_bridge(dev);
+
+	if (bridge->release_fn)
+		bridge->release_fn(bridge);
+
+	pci_free_resource_list(&bridge->windows);
+
+	kfree(bridge);
+}
+
 static struct pci_host_bridge *pci_alloc_host_bridge(struct pci_bus *b)
 {
 	struct pci_host_bridge *bridge;
 
 	bridge = kzalloc(sizeof(*bridge), GFP_KERNEL);
-	if (bridge) {
-		INIT_LIST_HEAD(&bridge->windows);
-		bridge->bus = b;
-	}
+	if (!bridge)
+		return NULL;
 
+	INIT_LIST_HEAD(&bridge->windows);
+	bridge->bus = b;
 	return bridge;
 }
 
@@ -1132,6 +1169,8 @@ static void pci_release_dev(struct device *dev)
 	pci_dev = to_pci_dev(dev);
 	pci_release_capabilities(pci_dev);
 	pci_release_of_node(pci_dev);
+	pcibios_release_device(pci_dev);
+	pci_bus_put(pci_dev->bus);
 	kfree(pci_dev);
 }
 
@@ -1188,19 +1227,7 @@ int pci_cfg_space_size(struct pci_dev *dev)
 	return PCI_CFG_SPACE_SIZE;
 }
 
-static void pci_release_bus_bridge_dev(struct device *dev)
-{
-	struct pci_host_bridge *bridge = to_pci_host_bridge(dev);
-
-	if (bridge->release_fn)
-		bridge->release_fn(bridge);
-
-	pci_free_resource_list(&bridge->windows);
-
-	kfree(bridge);
-}
-
-struct pci_dev *alloc_pci_dev(void)
+struct pci_dev *pci_alloc_dev(struct pci_bus *bus)
 {
 	struct pci_dev *dev;
 
@@ -1210,9 +1237,16 @@ struct pci_dev *alloc_pci_dev(void)
 
 	INIT_LIST_HEAD(&dev->bus_list);
 	dev->dev.type = &pci_dev_type;
+	dev->bus = pci_bus_get(bus);
 
 	return dev;
 }
+EXPORT_SYMBOL(pci_alloc_dev);
+
+struct pci_dev *alloc_pci_dev(void)
+{
+	return pci_alloc_dev(NULL);
+}
 EXPORT_SYMBOL(alloc_pci_dev);
 
 bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
@@ -1263,11 +1297,10 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn)
 	if (!pci_bus_read_dev_vendor_id(bus, devfn, &l, 60*1000))
 		return NULL;
 
-	dev = alloc_pci_dev();
+	dev = pci_alloc_dev(bus);
 	if (!dev)
 		return NULL;
 
-	dev->bus = bus;
 	dev->devfn = devfn;
 	dev->vendor = l & 0xffff;
 	dev->device = (l >> 16) & 0xffff;
@@ -1275,6 +1308,7 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn)
 	pci_set_of_node(dev);
 
 	if (pci_setup_device(dev)) {
+		pci_bus_put(dev->bus);
 		kfree(dev);
 		return NULL;
 	}
@@ -1462,24 +1496,23 @@ 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)
@@ -1554,6 +1587,22 @@ 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;
@@ -1561,13 +1610,18 @@ 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));
 
@@ -1578,25 +1632,25 @@ 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);
@@ -1700,15 +1754,19 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 		goto err_out;
 
 	bridge->dev.parent = parent;
-	bridge->dev.release = pci_release_bus_bridge_dev;
+	bridge->dev.release = pci_release_host_bridge_dev;
 	dev_set_name(&bridge->dev, "pci%04x:%02x", pci_domain_nr(b), bus);
 	error = pcibios_root_bridge_prepare(bridge);
-	if (error)
-		goto bridge_dev_reg_err;
+	if (error) {
+		kfree(bridge);
+		goto err_out;
+	}
 
 	error = device_register(&bridge->dev);
-	if (error)
-		goto bridge_dev_reg_err;
+	if (error) {
+		put_device(&bridge->dev);
+		goto err_out;
+	}
 	b->bridge = get_device(&bridge->dev);
 	device_enable_async_suspend(b->bridge);
 	pci_set_bus_of_node(b);
@@ -1764,8 +1822,6 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 class_dev_reg_err:
 	put_device(&bridge->dev);
 	device_unregister(&bridge->dev);
-bridge_dev_reg_err:
-	kfree(bridge);
 err_out:
 	kfree(b);
 	return NULL;
@@ -1948,7 +2004,6 @@ unsigned int __ref pci_rescan_bus(struct pci_bus *bus)
 
 	max = pci_scan_child_bus(bus);
 	pci_assign_unassigned_bus_resources(bus);
-	pci_enable_bridges(bus);
 	pci_bus_add_devices(bus);
 
 	return max;