Merge branches 'pci/enumeration', 'pci/hotplug', 'pci/misc', 'pci/numa' and...

Merge branches 'pci/enumeration', 'pci/hotplug', 'pci/misc', 'pci/numa' and 'pci/virtualization' into next

* pci/enumeration:
  PCI: Remove fixed parameter in pci_iov_resource_bar()
  PCI: Add informational printk for invalid BARs
  PCI: Shrink decoding-disabled window while sizing BARs
  PCI: Restore detection of read-only BARs

* pci/hotplug:
  PCI: Remove unused and broken to_hotplug_slot()

* pci/misc:
  PCI: Make FLR and AF FLR reset warning messages different
  PCI: Simplify if-return sequences
  PCI: Delete unnecessary NULL pointer checks

* pci/numa:
  PCI: Allow numa_node override via sysfs

* pci/virtualization:
  xen/pcifront: Process failure for pcifront_(re)scan_root()

Documentation/ABI/testing/sysfs-bus-pci

@@ -281,3 +281,16 @@ Description:
 		opt-out of driver binding using a driver_override name such as
 		"none".  Only a single driver may be specified in the override,
 		there is no support for parsing delimiters.
+
+What:		/sys/bus/pci/devices/.../numa_node
+Date:		Oct 2014
+Contact:	Prarit Bhargava <prarit@redhat.com>
+Description:
+		This file contains the NUMA node to which the PCI device is
+		attached, or -1 if the node is unknown.  The initial value
+		comes from an ACPI _PXM method or a similar firmware
+		source.  If that is missing or incorrect, this file can be
+		written to override the node.  In that case, please report
+		a firmware bug to the system vendor.  Writing to this file
+		taints the kernel with TAINT_FIRMWARE_WORKAROUND, which
+		reduces the supportability of your system.

drivers/pci/hotplug/ibmphp_res.c

@@ -376,10 +376,7 @@ int __init ibmphp_rsrc_init (void)
 		if (rc)
 			return rc;
 	}
-	rc = once_over ();  /* This is to align ranges (so no -1) */
-	if (rc)
-		return rc;
-	return 0;
+	return once_over ();	/* This is to align ranges (so no -1) */
 }
 
 /********************************************************************************

drivers/pci/iov.c

@@ -479,20 +479,16 @@ void pci_iov_release(struct pci_dev *dev)
  * pci_iov_resource_bar - get position of the SR-IOV BAR
  * @dev: the PCI device
  * @resno: the resource number
- * @type: the BAR type to be filled in
  *
  * Returns position of the BAR encapsulated in the SR-IOV capability.
  */
-int pci_iov_resource_bar(struct pci_dev *dev, int resno,
-			 enum pci_bar_type *type)
+int pci_iov_resource_bar(struct pci_dev *dev, int resno)
 {
 	if (resno < PCI_IOV_RESOURCES || resno > PCI_IOV_RESOURCE_END)
 		return 0;
 
 	BUG_ON(!dev->is_physfn);
 
-	*type = pci_bar_unknown;
-
 	return dev->sriov->pos + PCI_SRIOV_BAR +
 		4 * (resno - PCI_IOV_RESOURCES);
 }
@@ -510,13 +506,12 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno,
 resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno)
 {
 	struct resource tmp;
-	enum pci_bar_type type;
-	int reg = pci_iov_resource_bar(dev, resno, &type);
+	int reg = pci_iov_resource_bar(dev, resno);
 
 	if (!reg)
 		return 0;
 
-	 __pci_read_base(dev, type, &tmp, reg);
+	 __pci_read_base(dev, pci_bar_unknown, &tmp, reg);
 	return resource_alignment(&tmp);
 }
 

drivers/pci/pci-acpi.c

@@ -322,7 +322,6 @@ static void pci_acpi_wake_dev(struct work_struct *work)
 	pci_wakeup_event(pci_dev);
 	pm_runtime_resume(&pci_dev->dev);
 
-	if (pci_dev->subordinate)
 	pci_pme_wakeup_bus(pci_dev->subordinate);
 }
 

drivers/pci/pci-sysfs.c

@@ -221,12 +221,37 @@ static ssize_t enabled_show(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR_RW(enabled);
 
 #ifdef CONFIG_NUMA
+static ssize_t numa_node_store(struct device *dev,
+			       struct device_attribute *attr, const char *buf,
+			       size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int node, ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	ret = kstrtoint(buf, 0, &node);
+	if (ret)
+		return ret;
+
+	if (!node_online(node))
+		return -EINVAL;
+
+	add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+	dev_alert(&pdev->dev, FW_BUG "Overriding NUMA node to %d.  Contact your vendor for updates.",
+		  node);
+
+	dev->numa_node = node;
+	return count;
+}
+
 static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr,
 			      char *buf)
 {
 	return sprintf(buf, "%d\n", dev->numa_node);
 }
-static DEVICE_ATTR_RO(numa_node);
+static DEVICE_ATTR_RW(numa_node);
 #endif
 
 static ssize_t dma_mask_bits_show(struct device *dev,

drivers/pci/pci.c

@@ -1012,11 +1012,7 @@ int pci_save_state(struct pci_dev *dev)
 	if (i != 0)
 		return i;
 
-	i = pci_save_vc_state(dev);
-	if (i != 0)
-		return i;
-
-	return 0;
+	return pci_save_vc_state(dev);
 }
 EXPORT_SYMBOL(pci_save_state);
 
@@ -3144,12 +3140,10 @@ static int pcie_flr(struct pci_dev *dev, int probe)
 		return 0;
 
 	if (!pci_wait_for_pending_transaction(dev))
-		dev_err(&dev->dev, "transaction is not cleared; proceeding with reset anyway\n");
+		dev_err(&dev->dev, "timed out waiting for pending transaction; performing function level reset anyway\n");
 
 	pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR);
-
 	msleep(100);
-
 	return 0;
 }
 
@@ -3174,16 +3168,12 @@ static int pci_af_flr(struct pci_dev *dev, int probe)
 	 * is used, so we use the conrol offset rather than status and shift
 	 * the test bit to match.
 	 */
-	if (pci_wait_for_pending(dev, pos + PCI_AF_CTRL,
+	if (!pci_wait_for_pending(dev, pos + PCI_AF_CTRL,
 				 PCI_AF_STATUS_TP << 8))
-		goto clear;
-
-	dev_err(&dev->dev, "transaction is not cleared; proceeding with reset anyway\n");
+		dev_err(&dev->dev, "timed out waiting for pending transaction; performing AF function level reset anyway\n");
 
-clear:
 	pci_write_config_byte(dev, pos + PCI_AF_CTRL, PCI_AF_CTRL_FLR);
 	msleep(100);
-
 	return 0;
 }
 
@@ -4180,7 +4170,8 @@ int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type)
 		return dev->rom_base_reg;
 	} else if (resno < PCI_BRIDGE_RESOURCES) {
 		/* device specific resource */
-		reg = pci_iov_resource_bar(dev, resno, type);
+		*type = pci_bar_unknown;
+		reg = pci_iov_resource_bar(dev, resno);
 		if (reg)
 			return reg;
 	}

drivers/pci/pci.h

@@ -251,8 +251,7 @@ static inline void pci_restore_ats_state(struct pci_dev *dev)
 #ifdef CONFIG_PCI_IOV
 int pci_iov_init(struct pci_dev *dev);
 void pci_iov_release(struct pci_dev *dev);
-int pci_iov_resource_bar(struct pci_dev *dev, int resno,
-			 enum pci_bar_type *type);
+int pci_iov_resource_bar(struct pci_dev *dev, int resno);
 resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno);
 void pci_restore_iov_state(struct pci_dev *dev);
 int pci_iov_bus_range(struct pci_bus *bus);
@@ -266,8 +265,7 @@ static inline void pci_iov_release(struct pci_dev *dev)
 
 {
 }
-static inline int pci_iov_resource_bar(struct pci_dev *dev, int resno,
-				       enum pci_bar_type *type)
+static inline int pci_iov_resource_bar(struct pci_dev *dev, int resno)
 {
 	return 0;
 }

drivers/pci/probe.c

@@ -87,7 +87,6 @@ static void release_pcibus_dev(struct device *dev)
 {
 	struct pci_bus *pci_bus = to_pci_bus(dev);
 
-	if (pci_bus->bridge)
 	put_device(pci_bus->bridge);
 	pci_bus_remove_resources(pci_bus);
 	pci_release_bus_of_node(pci_bus);
@@ -175,7 +174,6 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 	u64 l64, sz64, mask64;
 	u16 orig_cmd;
 	struct pci_bus_region region, inverted_region;
-	bool bar_too_big = false, bar_too_high = false, bar_invalid = false;
 
 	mask = type ? PCI_ROM_ADDRESS_MASK : ~0;
 
@@ -201,8 +199,8 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 	 * memory BAR or a ROM, bit 0 must be clear; if it's an io BAR, bit
 	 * 1 must be clear.
 	 */
-	if (!sz || sz == 0xffffffff)
-		goto fail;
+	if (sz == 0xffffffff)
+		sz = 0;
 
 	/*
 	 * I don't know how l can have all bits set.  Copied from old code.
@@ -215,23 +213,22 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		res->flags = decode_bar(dev, l);
 		res->flags |= IORESOURCE_SIZEALIGN;
 		if (res->flags & IORESOURCE_IO) {
-			l &= PCI_BASE_ADDRESS_IO_MASK;
-			mask = PCI_BASE_ADDRESS_IO_MASK & (u32) IO_SPACE_LIMIT;
+			l64 = l & PCI_BASE_ADDRESS_IO_MASK;
+			sz64 = sz & PCI_BASE_ADDRESS_IO_MASK;
+			mask64 = PCI_BASE_ADDRESS_IO_MASK & (u32)IO_SPACE_LIMIT;
 		} else {
-			l &= PCI_BASE_ADDRESS_MEM_MASK;
-			mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
+			l64 = l & PCI_BASE_ADDRESS_MEM_MASK;
+			sz64 = sz & PCI_BASE_ADDRESS_MEM_MASK;
+			mask64 = (u32)PCI_BASE_ADDRESS_MEM_MASK;
 		}
 	} else {
 		res->flags |= (l & IORESOURCE_ROM_ENABLE);
-		l &= PCI_ROM_ADDRESS_MASK;
-		mask = (u32)PCI_ROM_ADDRESS_MASK;
+		l64 = l & PCI_ROM_ADDRESS_MASK;
+		sz64 = sz & PCI_ROM_ADDRESS_MASK;
+		mask64 = (u32)PCI_ROM_ADDRESS_MASK;
 	}
 
 	if (res->flags & IORESOURCE_MEM_64) {
-		l64 = l;
-		sz64 = sz;
-		mask64 = mask | (u64)~0 << 32;
-
 		pci_read_config_dword(dev, pos + 4, &l);
 		pci_write_config_dword(dev, pos + 4, ~0);
 		pci_read_config_dword(dev, pos + 4, &sz);
@@ -239,18 +236,30 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 
 		l64 |= ((u64)l << 32);
 		sz64 |= ((u64)sz << 32);
+		mask64 |= ((u64)~0 << 32);
+	}
 
-		sz64 = pci_size(l64, sz64, mask64);
+	if (!dev->mmio_always_on && (orig_cmd & PCI_COMMAND_DECODE_ENABLE))
+		pci_write_config_word(dev, PCI_COMMAND, orig_cmd);
 
 	if (!sz64)
 		goto fail;
 
+	sz64 = pci_size(l64, sz64, mask64);
+	if (!sz64) {
+		dev_info(&dev->dev, FW_BUG "reg 0x%x: invalid BAR (can't size)\n",
+			 pos);
+		goto fail;
+	}
+
+	if (res->flags & IORESOURCE_MEM_64) {
 		if ((sizeof(dma_addr_t) < 8 || sizeof(resource_size_t) < 8) &&
 		    sz64 > 0x100000000ULL) {
 			res->flags |= IORESOURCE_UNSET | IORESOURCE_DISABLED;
 			res->start = 0;
 			res->end = 0;
-			bar_too_big = true;
+			dev_err(&dev->dev, "reg 0x%x: can't handle BAR larger than 4GB (size %#010llx)\n",
+				pos, (unsigned long long)sz64);
 			goto out;
 		}
 
@@ -259,22 +268,15 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 			res->flags |= IORESOURCE_UNSET;
 			res->start = 0;
 			res->end = sz64;
-			bar_too_high = true;
+			dev_info(&dev->dev, "reg 0x%x: can't handle BAR above 4GB (bus address %#010llx)\n",
+				 pos, (unsigned long long)l64);
 			goto out;
-		} else {
-			region.start = l64;
-			region.end = l64 + sz64;
 		}
-	} else {
-		sz = pci_size(l, sz, mask);
-
-		if (!sz)
-			goto fail;
-
-		region.start = l;
-		region.end = l + sz;
 	}
 
+	region.start = l64;
+	region.end = l64 + sz64;
+
 	pcibios_bus_to_resource(dev->bus, res, &region);
 	pcibios_resource_to_bus(dev->bus, &inverted_region, res);
 
@@ -293,7 +295,8 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		res->flags |= IORESOURCE_UNSET;
 		res->start = 0;
 		res->end = region.end - region.start;
-		bar_invalid = true;
+		dev_info(&dev->dev, "reg 0x%x: initial BAR value %#010llx invalid\n",
+			 pos, (unsigned long long)region.start);
 	}
 
 	goto out;
@@ -302,19 +305,6 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 fail:
 	res->flags = 0;
 out:
-	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 0x%x: can't handle BAR larger than 4GB (size %#010llx)\n",
-			pos, (unsigned long long) sz64);
-	if (bar_too_high)
-		dev_info(&dev->dev, "reg 0x%x: can't handle BAR above 4G (bus address %#010llx)\n",
-			 pos, (unsigned long long) l64);
-	if (bar_invalid)
-		dev_info(&dev->dev, "reg 0x%x: initial BAR value %#010llx invalid\n",
-			 pos, (unsigned long long) region.start);
 	if (res->flags)
 		dev_printk(KERN_DEBUG, &dev->dev, "reg 0x%x: %pR\n", pos, res);
 

drivers/pci/search.c

@@ -271,7 +271,6 @@ static struct pci_dev *pci_get_dev_by_id(const struct pci_device_id *id,
 			      match_pci_dev_by_id);
 	if (dev)
 		pdev = to_pci_dev(dev);
-	if (from)
 	pci_dev_put(from);
 	return pdev;
 }

drivers/pci/xen-pcifront.c

@@ -596,7 +596,6 @@ static pci_ers_result_t pcifront_common_process(int cmd,
 	pcidev = pci_get_bus_and_slot(bus, devfn);
 	if (!pcidev || !pcidev->driver) {
 		dev_err(&pdev->xdev->dev, "device or AER driver is NULL\n");
-		if (pcidev)
 		pci_dev_put(pcidev);
 		return result;
 	}
@@ -866,6 +865,11 @@ static int pcifront_try_connect(struct pcifront_device *pdev)
 		xenbus_dev_error(pdev->xdev, err,
 				 "No PCI Roots found, trying 0000:00");
 		err = pcifront_scan_root(pdev, 0, 0);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root 0000:00");
+			goto out;
+		}
 		num_roots = 0;
 	} else if (err != 1) {
 		if (err == 0)
@@ -947,6 +951,11 @@ static int pcifront_attach_devices(struct pcifront_device *pdev)
 		xenbus_dev_error(pdev->xdev, err,
 				 "No PCI Roots found, trying 0000:00");
 		err = pcifront_rescan_root(pdev, 0, 0);
+		if (err) {
+			xenbus_dev_fatal(pdev->xdev, err,
+					 "Error scanning PCI root 0000:00");
+			goto out;
+		}
 		num_roots = 0;
 	} else if (err != 1) {
 		if (err == 0)

include/linux/pci_hotplug.h

@@ -109,7 +109,6 @@ struct hotplug_slot {
 	struct list_head		slot_list;
 	struct pci_slot			*pci_slot;
 };
-#define to_hotplug_slot(n) container_of(n, struct hotplug_slot, kobj)
 
 static inline const char *hotplug_slot_name(const struct hotplug_slot *slot)
 {