Merge tag 'pci-v3.14-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci

Pull PCI updates from Bjorn Helgaas:
 "PCI changes for the v3.14 merge window:

  Resource management
    - Change pci_bus_region addresses to dma_addr_t (Bjorn Helgaas)
    - Support 64-bit AGP BARs (Bjorn Helgaas, Yinghai Lu)
    - Add pci_bus_address() to get bus address of a BAR (Bjorn Helgaas)
    - Use pci_resource_start() for CPU address of AGP BARs (Bjorn Helgaas)
    - Enforce bus address limits in resource allocation (Yinghai Lu)
    - Allocate 64-bit BARs above 4G when possible (Yinghai Lu)
    - Convert pcibios_resource_to_bus() to take pci_bus, not pci_dev (Yinghai Lu)

  PCI device hotplug
    - Major rescan/remove locking update (Rafael J. Wysocki)
    - Make ioapic builtin only (not modular) (Yinghai Lu)
    - Fix release/free issues (Yinghai Lu)
    - Clean up pciehp (Bjorn Helgaas)
    - Announce pciehp slot info during enumeration (Bjorn Helgaas)

  MSI
    - Add pci_msi_vec_count(), pci_msix_vec_count() (Alexander Gordeev)
    - Add pci_enable_msi_range(), pci_enable_msix_range() (Alexander Gordeev)
    - Deprecate "tri-state" interfaces: fail/success/fail+info (Alexander Gordeev)
    - Export MSI mode using attributes, not kobjects (Greg Kroah-Hartman)
    - Drop "irq" param from *_restore_msi_irqs() (DuanZhenzhong)

  SR-IOV
    - Clear NumVFs when disabling SR-IOV in sriov_init() (ethan.zhao)

  Virtualization
    - Add support for save/restore of extended capabilities (Alex Williamson)
    - Add Virtual Channel to save/restore support (Alex Williamson)
    - Never treat a VF as a multifunction device (Alex Williamson)
    - Add pci_try_reset_function(), et al (Alex Williamson)

  AER
    - Ignore non-PCIe error sources (Betty Dall)
    - Support ACPI HEST error sources for domains other than 0 (Betty Dall)
    - Consolidate HEST error source parsers (Bjorn Helgaas)
    - Add a TLP header print helper (Borislav Petkov)

  Freescale i.MX6
    - Remove unnecessary code (Fabio Estevam)
    - Make reset-gpio optional (Marek Vasut)
    - Report "link up" only after link training completes (Marek Vasut)
    - Start link in Gen1 before negotiating for Gen2 mode (Marek Vasut)
    - Fix PCIe startup code (Richard Zhu)

  Marvell MVEBU
    - Remove duplicate of_clk_get_by_name() call (Andrew Lunn)
    - Drop writes to bridge Secondary Status register (Jason Gunthorpe)
    - Obey bridge PCI_COMMAND_MEM and PCI_COMMAND_IO bits (Jason Gunthorpe)
    - Support a bridge with no IO port window (Jason Gunthorpe)
    - Use max_t() instead of max(resource_size_t,) (Jingoo Han)
    - Remove redundant of_match_ptr (Sachin Kamat)
    - Call pci_ioremap_io() at startup instead of dynamically (Thomas Petazzoni)

  NVIDIA Tegra
    - Disable Gen2 for Tegra20 and Tegra30 (Eric Brower)

  Renesas R-Car
    - Add runtime PM support (Valentine Barshak)
    - Fix rcar_pci_probe() return value check (Wei Yongjun)

  Synopsys DesignWare
    - Fix crash in dw_msi_teardown_irq() (Bjørn Erik Nilsen)
    - Remove redundant call to pci_write_config_word() (Bjørn Erik Nilsen)
    - Fix missing MSI IRQs (Harro Haan)
    - Add dw_pcie prefix before cfg_read/write (Pratyush Anand)
    - Fix I/O transfers by using CPU (not realio) address (Pratyush Anand)
    - Whitespace cleanup (Jingoo Han)

  EISA
    - Call put_device() if device_register() fails (Levente Kurusa)
    - Revert EISA initialization breakage ((Bjorn Helgaas)

  Miscellaneous
    - Remove unused code, including PCIe 3.0 interfaces (Stephen Hemminger)
    - Prevent bus conflicts while checking for bridge apertures (Bjorn Helgaas)
    - Stop clearing bridge Secondary Status when setting up I/O aperture (Bjorn Helgaas)
    - Use dev_is_pci() to identify PCI devices (Yijing Wang)
    - Deprecate DEFINE_PCI_DEVICE_TABLE (Joe Perches)
    - Update documentation 00-INDEX (Erik Ekman)"

* tag 'pci-v3.14-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (119 commits)
  Revert "EISA: Initialize device before its resources"
  Revert "EISA: Log device resources in dmesg"
  vfio-pci: Use pci "try" reset interface
  PCI: Check parent kobject in pci_destroy_dev()
  xen/pcifront: Use global PCI rescan-remove locking
  powerpc/eeh: Use global PCI rescan-remove locking
  PCI: Fix pci_check_and_unmask_intx() comment typos
  PCI: Add pci_try_reset_function(), pci_try_reset_slot(), pci_try_reset_bus()
  MPT / PCI: Use pci_stop_and_remove_bus_device_locked()
  platform / x86: Use global PCI rescan-remove locking
  PCI: hotplug: Use global PCI rescan-remove locking
  pcmcia: Use global PCI rescan-remove locking
  ACPI / hotplug / PCI: Use global PCI rescan-remove locking
  ACPI / PCI: Use global PCI rescan-remove locking in PCI root hotplug
  PCI: Add global pci_lock_rescan_remove()
  PCI: Cleanup pci.h whitespace
  PCI: Reorder so actual code comes before stubs
  PCI/AER: Support ACPI HEST AER error sources for PCI domains other than 0
  ACPICA: Add helper macros to extract bus/segment numbers from HEST table.
  PCI: Make local functions static
  ...

Documentation/ABI/testing/sysfs-bus-pci

@@ -70,18 +70,15 @@ Date:		September, 2011
 Contact:	Neil Horman <nhorman@tuxdriver.com>
 Description:
 		The /sys/devices/.../msi_irqs directory contains a variable set
-		of sub-directories, with each sub-directory being named after a
-		corresponding msi irq vector allocated to that device.  Each
-		numbered sub-directory N contains attributes of that irq.
-		Note that this directory is not created for device drivers which
-		do not support msi irqs
+		of files, with each file being named after a corresponding msi
+		irq vector allocated to that device.
 
-What:		/sys/bus/pci/devices/.../msi_irqs/<N>/mode
+What:		/sys/bus/pci/devices/.../msi_irqs/<N>
 Date:		September 2011
 Contact:	Neil Horman <nhorman@tuxdriver.com>
 Description:
 		This attribute indicates the mode that the irq vector named by
-		the parent directory is in (msi vs. msix)
+		the file is in (msi vs. msix)
 
 What:		/sys/bus/pci/devices/.../remove
 Date:		January 2009

Documentation/PCI/00-INDEX

@@ -2,12 +2,12 @@
 	- this file
 MSI-HOWTO.txt
 	- the Message Signaled Interrupts (MSI) Driver Guide HOWTO and FAQ.
-PCI-DMA-mapping.txt
-	- info for PCI drivers using DMA portably across all platforms
 PCIEBUS-HOWTO.txt
 	- a guide describing the PCI Express Port Bus driver
 pci-error-recovery.txt
 	- info on PCI error recovery
+pci-iov-howto.txt
+	- the PCI Express I/O Virtualization HOWTO
 pci.txt
 	- info on the PCI subsystem for device driver authors
 pcieaer-howto.txt

Documentation/PCI/MSI-HOWTO.txt

@@ -82,93 +82,111 @@ Most of the hard work is done for the driver in the PCI layer.  It simply
 has to request that the PCI layer set up the MSI capability for this
 device.
 
-4.2.1 pci_enable_msi
+4.2.1 pci_enable_msi_range
 
-int pci_enable_msi(struct pci_dev *dev)
+int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
 
-A successful call allocates ONE interrupt to the device, regardless
-of how many MSIs the device supports.  The device is switched from
-pin-based interrupt mode to MSI mode.  The dev->irq number is changed
-to a new number which represents the message signaled interrupt;
-consequently, this function should be called before the driver calls
-request_irq(), because an MSI is delivered via a vector that is
-different from the vector of a pin-based interrupt.
+This function allows a device driver to request any number of MSI
+interrupts within specified range from 'minvec' to 'maxvec'.
 
-4.2.2 pci_enable_msi_block
-
-int pci_enable_msi_block(struct pci_dev *dev, int count)
-
-This variation on the above call allows a device driver to request multiple
-MSIs.  The MSI specification only allows interrupts to be allocated in
-powers of two, up to a maximum of 2^5 (32).
-
-If this function returns 0, it has succeeded in allocating at least as many
-interrupts as the driver requested (it may have allocated more in order
-to satisfy the power-of-two requirement).  In this case, the function
-enables MSI on this device and updates dev->irq to be the lowest of
-the new interrupts assigned to it.  The other interrupts assigned to
-the device are in the range dev->irq to dev->irq + count - 1.
-
-If this function returns a negative number, it indicates an error and
-the driver should not attempt to request any more MSI interrupts for
-this device.  If this function returns a positive number, it is
-less than 'count' and indicates the number of interrupts that could have
-been allocated.  In neither case is the irq value updated or the device
-switched into MSI mode.
-
-The device driver must decide what action to take if
-pci_enable_msi_block() returns a value less than the number requested.
-For instance, the driver could still make use of fewer interrupts;
-in this case the driver should call pci_enable_msi_block()
-again.  Note that it is not guaranteed to succeed, even when the
-'count' has been reduced to the value returned from a previous call to
-pci_enable_msi_block().  This is because there are multiple constraints
-on the number of vectors that can be allocated; pci_enable_msi_block()
-returns as soon as it finds any constraint that doesn't allow the
-call to succeed.
-
-4.2.3 pci_enable_msi_block_auto
-
-int pci_enable_msi_block_auto(struct pci_dev *dev, unsigned int *count)
-
-This variation on pci_enable_msi() call allows a device driver to request
-the maximum possible number of MSIs.  The MSI specification only allows
-interrupts to be allocated in powers of two, up to a maximum of 2^5 (32).
-
-If this function returns a positive number, it indicates that it has
-succeeded and the returned value is the number of allocated interrupts. In
-this case, the function enables MSI on this device and updates dev->irq to
-be the lowest of the new interrupts assigned to it.  The other interrupts
-assigned to the device are in the range dev->irq to dev->irq + returned
-value - 1.
+If this function returns a positive number it indicates the number of
+MSI interrupts that have been successfully allocated.  In this case
+the device is switched from pin-based interrupt mode to MSI mode and
+updates dev->irq to be the lowest of the new interrupts assigned to it.
+The other interrupts assigned to the device are in the range dev->irq
+to dev->irq + returned value - 1.  Device driver can use the returned
+number of successfully allocated MSI interrupts to further allocate
+and initialize device resources.
 
 If this function returns a negative number, it indicates an error and
 the driver should not attempt to request any more MSI interrupts for
 this device.
 
-If the device driver needs to know the number of interrupts the device
-supports it can pass the pointer count where that number is stored. The
-device driver must decide what action to take if pci_enable_msi_block_auto()
-succeeds, but returns a value less than the number of interrupts supported.
-If the device driver does not need to know the number of interrupts
-supported, it can set the pointer count to NULL.
+This function should be called before the driver calls request_irq(),
+because MSI interrupts are delivered via vectors that are different
+from the vector of a pin-based interrupt.
 
-4.2.4 pci_disable_msi
+It is ideal if drivers can cope with a variable number of MSI interrupts;
+there are many reasons why the platform may not be able to provide the
+exact number that a driver asks for.
+
+There could be devices that can not operate with just any number of MSI
+interrupts within a range.  See chapter 4.3.1.3 to get the idea how to
+handle such devices for MSI-X - the same logic applies to MSI.
+
+4.2.1.1 Maximum possible number of MSI interrupts
+
+The typical usage of MSI interrupts is to allocate as many vectors as
+possible, likely up to the limit returned by pci_msi_vec_count() function:
+
+static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec)
+{
+	return pci_enable_msi_range(pdev, 1, nvec);
+}
+
+Note the value of 'minvec' parameter is 1.  As 'minvec' is inclusive,
+the value of 0 would be meaningless and could result in error.
+
+Some devices have a minimal limit on number of MSI interrupts.
+In this case the function could look like this:
+
+static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec)
+{
+	return pci_enable_msi_range(pdev, FOO_DRIVER_MINIMUM_NVEC, nvec);
+}
+
+4.2.1.2 Exact number of MSI interrupts
+
+If a driver is unable or unwilling to deal with a variable number of MSI
+interrupts it could request a particular number of interrupts by passing
+that number to pci_enable_msi_range() function as both 'minvec' and 'maxvec'
+parameters:
+
+static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec)
+{
+	return pci_enable_msi_range(pdev, nvec, nvec);
+}
+
+4.2.1.3 Single MSI mode
+
+The most notorious example of the request type described above is
+enabling the single MSI mode for a device.  It could be done by passing
+two 1s as 'minvec' and 'maxvec':
+
+static int foo_driver_enable_single_msi(struct pci_dev *pdev)
+{
+	return pci_enable_msi_range(pdev, 1, 1);
+}
+
+4.2.2 pci_disable_msi
 
 void pci_disable_msi(struct pci_dev *dev)
 
-This function should be used to undo the effect of pci_enable_msi() or
-pci_enable_msi_block() or pci_enable_msi_block_auto().  Calling it restores
-dev->irq to the pin-based interrupt number and frees the previously
-allocated message signaled interrupt(s).  The interrupt may subsequently be
-assigned to another device, so drivers should not cache the value of
-dev->irq.
+This function should be used to undo the effect of pci_enable_msi_range().
+Calling it restores dev->irq to the pin-based interrupt number and frees
+the previously allocated MSIs.  The interrupts may subsequently be assigned
+to another device, so drivers should not cache the value of dev->irq.
 
 Before calling this function, a device driver must always call free_irq()
 on any interrupt for which it previously called request_irq().
 Failure to do so results in a BUG_ON(), leaving the device with
 MSI enabled and thus leaking its vector.
 
+4.2.3 pci_msi_vec_count
+
+int pci_msi_vec_count(struct pci_dev *dev)
+
+This function could be used to retrieve the number of MSI vectors the
+device requested (via the Multiple Message Capable register). The MSI
+specification only allows the returned value to be a power of two,
+up to a maximum of 2^5 (32).
+
+If this function returns a negative number, it indicates the device is
+not capable of sending MSIs.
+
+If this function returns a positive number, it indicates the maximum
+number of MSI interrupt vectors that could be allocated.
+
 4.3 Using MSI-X
 
 The MSI-X capability is much more flexible than the MSI capability.
@@ -188,26 +206,31 @@ in each element of the array to indicate for which entries the kernel
 should assign interrupts; it is invalid to fill in two entries with the
 same number.
 
-4.3.1 pci_enable_msix
+4.3.1 pci_enable_msix_range
 
-int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
+int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
+			  int minvec, int maxvec)
 
-Calling this function asks the PCI subsystem to allocate 'nvec' MSIs.
+Calling this function asks the PCI subsystem to allocate any number of
+MSI-X interrupts within specified range from 'minvec' to 'maxvec'.
 The 'entries' argument is a pointer to an array of msix_entry structs
-which should be at least 'nvec' entries in size.  On success, the
-device is switched into MSI-X mode and the function returns 0.
-The 'vector' member in each entry is populated with the interrupt number;
+which should be at least 'maxvec' entries in size.
+
+On success, the device is switched into MSI-X mode and the function
+returns the number of MSI-X interrupts that have been successfully
+allocated.  In this case the 'vector' member in entries numbered from
+0 to the returned value - 1 is populated with the interrupt number;
 the driver should then call request_irq() for each 'vector' that it
 decides to use.  The device driver is responsible for keeping track of the
 interrupts assigned to the MSI-X vectors so it can free them again later.
+Device driver can use the returned number of successfully allocated MSI-X
+interrupts to further allocate and initialize device resources.
 
 If this function returns a negative number, it indicates an error and
 the driver should not attempt to allocate any more MSI-X interrupts for
-this device.  If it returns a positive number, it indicates the maximum
-number of interrupt vectors that could have been allocated. See example
-below.
+this device.
 
-This function, in contrast with pci_enable_msi(), does not adjust
+This function, in contrast with pci_enable_msi_range(), does not adjust
 dev->irq.  The device will not generate interrupts for this interrupt
 number once MSI-X is enabled.
 
@@ -218,28 +241,103 @@ It is ideal if drivers can cope with a variable number of MSI-X interrupts;
 there are many reasons why the platform may not be able to provide the
 exact number that a driver asks for.
 
-A request loop to achieve that might look like:
+There could be devices that can not operate with just any number of MSI-X
+interrupts within a range.  E.g., an network adapter might need let's say
+four vectors per each queue it provides.  Therefore, a number of MSI-X
+interrupts allocated should be a multiple of four.  In this case interface
+pci_enable_msix_range() can not be used alone to request MSI-X interrupts
+(since it can allocate any number within the range, without any notion of
+the multiple of four) and the device driver should master a custom logic
+to request the required number of MSI-X interrupts.
+
+4.3.1.1 Maximum possible number of MSI-X interrupts
+
+The typical usage of MSI-X interrupts is to allocate as many vectors as
+possible, likely up to the limit returned by pci_msix_vec_count() function:
 
 static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
 {
-	while (nvec >= FOO_DRIVER_MINIMUM_NVEC) {
-		rc = pci_enable_msix(adapter->pdev,
-				     adapter->msix_entries, nvec);
-		if (rc > 0)
-			nvec = rc;
-		else
-			return rc;
+	return pci_enable_msi_range(adapter->pdev, adapter->msix_entries,
+				    1, nvec);
+}
+
+Note the value of 'minvec' parameter is 1.  As 'minvec' is inclusive,
+the value of 0 would be meaningless and could result in error.
+
+Some devices have a minimal limit on number of MSI-X interrupts.
+In this case the function could look like this:
+
+static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
+{
+	return pci_enable_msi_range(adapter->pdev, adapter->msix_entries,
+				    FOO_DRIVER_MINIMUM_NVEC, nvec);
+}
+
+4.3.1.2 Exact number of MSI-X interrupts
+
+If a driver is unable or unwilling to deal with a variable number of MSI-X
+interrupts it could request a particular number of interrupts by passing
+that number to pci_enable_msix_range() function as both 'minvec' and 'maxvec'
+parameters:
+
+static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
+{
+	return pci_enable_msi_range(adapter->pdev, adapter->msix_entries,
+				    nvec, nvec);
+}
+
+4.3.1.3 Specific requirements to the number of MSI-X interrupts
+
+As noted above, there could be devices that can not operate with just any
+number of MSI-X interrupts within a range.  E.g., let's assume a device that
+is only capable sending the number of MSI-X interrupts which is a power of
+two.  A routine that enables MSI-X mode for such device might look like this:
+
+/*
+ * Assume 'minvec' and 'maxvec' are non-zero
+ */
+static int foo_driver_enable_msix(struct foo_adapter *adapter,
+				  int minvec, int maxvec)
+{
+	int rc;
+
+	minvec = roundup_pow_of_two(minvec);
+	maxvec = rounddown_pow_of_two(maxvec);
+
+	if (minvec > maxvec)
+		return -ERANGE;
+
+retry:
+	rc = pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
+				   maxvec, maxvec);
+	/*
+	 * -ENOSPC is the only error code allowed to be analized
+	 */
+	if (rc == -ENOSPC) {
+		if (maxvec == 1)
+			return -ENOSPC;
+
+		maxvec /= 2;
+
+		if (minvec > maxvec)
+			return -ENOSPC;
+
+		goto retry;
 	}
 
-	return -ENOSPC;
+	return rc;
 }
 
+Note how pci_enable_msix_range() return value is analized for a fallback -
+any error code other than -ENOSPC indicates a fatal error and should not
+be retried.
+
 4.3.2 pci_disable_msix
 
 void pci_disable_msix(struct pci_dev *dev)
 
-This function should be used to undo the effect of pci_enable_msix().  It frees
-the previously allocated message signaled interrupts.  The interrupts may
+This function should be used to undo the effect of pci_enable_msix_range().
+It frees the previously allocated MSI-X interrupts. The interrupts may
 subsequently be assigned to another device, so drivers should not cache
 the value of the 'vector' elements over a call to pci_disable_msix().
 
@@ -255,18 +353,32 @@ MSI-X Table.  This address is mapped by the PCI subsystem, and should not
 be accessed directly by the device driver.  If the driver wishes to
 mask or unmask an interrupt, it should call disable_irq() / enable_irq().
 
+4.3.4 pci_msix_vec_count
+
+int pci_msix_vec_count(struct pci_dev *dev)
+
+This function could be used to retrieve number of entries in the device
+MSI-X table.
+
+If this function returns a negative number, it indicates the device is
+not capable of sending MSI-Xs.
+
+If this function returns a positive number, it indicates the maximum
+number of MSI-X interrupt vectors that could be allocated.
+
 4.4 Handling devices implementing both MSI and MSI-X capabilities
 
 If a device implements both MSI and MSI-X capabilities, it can
 run in either MSI mode or MSI-X mode, but not both simultaneously.
 This is a requirement of the PCI spec, and it is enforced by the
-PCI layer.  Calling pci_enable_msi() when MSI-X is already enabled or
-pci_enable_msix() when MSI is already enabled results in an error.
-If a device driver wishes to switch between MSI and MSI-X at runtime,
-it must first quiesce the device, then switch it back to pin-interrupt
-mode, before calling pci_enable_msi() or pci_enable_msix() and resuming
-operation.  This is not expected to be a common operation but may be
-useful for debugging or testing during development.
+PCI layer.  Calling pci_enable_msi_range() when MSI-X is already
+enabled or pci_enable_msix_range() when MSI is already enabled
+results in an error.  If a device driver wishes to switch between MSI
+and MSI-X at runtime, it must first quiesce the device, then switch
+it back to pin-interrupt mode, before calling pci_enable_msi_range()
+or pci_enable_msix_range() and resuming operation.  This is not expected
+to be a common operation but may be useful for debugging or testing
+during development.
 
 4.5 Considerations when using MSIs
 
@@ -381,5 +493,5 @@ or disabled (0).  If 0 is found in any of the msi_bus files belonging
 to bridges between the PCI root and the device, MSIs are disabled.
 
 It is also worth checking the device driver to see whether it supports MSIs.
-For example, it may contain calls to pci_enable_msi(), pci_enable_msix() or
-pci_enable_msi_block().
+For example, it may contain calls to pci_enable_msi_range() or
+pci_enable_msix_range().

Documentation/PCI/pci.txt

@@ -123,8 +123,10 @@ initialization with a pointer to a structure describing the driver
 
 
 The ID table is an array of struct pci_device_id entries ending with an
-all-zero entry; use of the macro DEFINE_PCI_DEVICE_TABLE is the preferred
-method of declaring the table.  Each entry consists of:
+all-zero entry.  Definitions with static const are generally preferred.
+Use of the deprecated macro DEFINE_PCI_DEVICE_TABLE should be avoided.
+
+Each entry consists of:
 
 	vendor,device	Vendor and device ID to match (or PCI_ANY_ID)
 

Documentation/devicetree/bindings/pci/designware-pcie.txt

@@ -19,6 +19,8 @@ Required properties:
 	to define the mapping of the PCIe interface to interrupt
 	numbers.
 - num-lanes: number of lanes to use
+
+Optional properties:
 - reset-gpio: gpio pin number of power good signal
 
 Optional properties for fsl,imx6q-pcie

arch/alpha/kernel/pci-sysfs.c

@@ -83,7 +83,7 @@ static int pci_mmap_resource(struct kobject *kobj,
 	if (iomem_is_exclusive(res->start))
 		return -EINVAL;
 
-	pcibios_resource_to_bus(pdev, &bar, res);
+	pcibios_resource_to_bus(pdev->bus, &bar, res);
 	vma->vm_pgoff += bar.start >> (PAGE_SHIFT - (sparse ? 5 : 0));
 	mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io;
 
@@ -139,7 +139,7 @@ static int sparse_mem_mmap_fits(struct pci_dev *pdev, int num)
 	long dense_offset;
 	unsigned long sparse_size;
 
-	pcibios_resource_to_bus(pdev, &bar, &pdev->resource[num]);
+	pcibios_resource_to_bus(pdev->bus, &bar, &pdev->resource[num]);
 
 	/* All core logic chips have 4G sparse address space, except
 	   CIA which has 16G (see xxx_SPARSE_MEM and xxx_DENSE_MEM

arch/alpha/kernel/pci_iommu.c

@@ -325,7 +325,7 @@ pci_map_single_1(struct pci_dev *pdev, void *cpu_addr, size_t size,
 /* Helper for generic DMA-mapping functions. */
 static struct pci_dev *alpha_gendev_to_pci(struct device *dev)
 {
-	if (dev && dev->bus == &pci_bus_type)
+	if (dev && dev_is_pci(dev))
 		return to_pci_dev(dev);
 
 	/* Assume that non-PCI devices asking for DMA are either ISA or EISA,

arch/arm/common/it8152.c

@@ -257,7 +257,7 @@ static int it8152_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t s
  */
 static int it8152_pci_platform_notify(struct device *dev)
 {
-	if (dev->bus == &pci_bus_type) {
+	if (dev_is_pci(dev)) {
 		if (dev->dma_mask)
 			*dev->dma_mask = (SZ_64M - 1) | PHYS_OFFSET;
 		dev->coherent_dma_mask = (SZ_64M - 1) | PHYS_OFFSET;
@@ -268,7 +268,7 @@ static int it8152_pci_platform_notify(struct device *dev)
 
 static int it8152_pci_platform_notify_remove(struct device *dev)
 {
-	if (dev->bus == &pci_bus_type)
+	if (dev_is_pci(dev))
 		dmabounce_unregister_dev(dev);
 
 	return 0;

arch/arm/mach-ixp4xx/common-pci.c

@@ -326,7 +326,7 @@ static int ixp4xx_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t s
  */
 static int ixp4xx_pci_platform_notify(struct device *dev)
 {
-	if(dev->bus == &pci_bus_type) {
+	if (dev_is_pci(dev)) {
 		*dev->dma_mask =  SZ_64M - 1;
 		dev->coherent_dma_mask = SZ_64M - 1;
 		dmabounce_register_dev(dev, 2048, 4096, ixp4xx_needs_bounce);
@@ -336,9 +336,9 @@ static int ixp4xx_pci_platform_notify(struct device *dev)
 
 static int ixp4xx_pci_platform_notify_remove(struct device *dev)
 {
-	if(dev->bus == &pci_bus_type) {
+	if (dev_is_pci(dev))
 		dmabounce_unregister_dev(dev);
-	}
+
 	return 0;
 }
 

arch/ia64/hp/common/sba_iommu.c

@@ -255,7 +255,7 @@ static u64 prefetch_spill_page;
 #endif
 
 #ifdef CONFIG_PCI
-# define GET_IOC(dev)	(((dev)->bus == &pci_bus_type)						\
+# define GET_IOC(dev)	((dev_is_pci(dev))						\
 			 ? ((struct ioc *) PCI_CONTROLLER(to_pci_dev(dev))->iommu) : NULL)
 #else
 # define GET_IOC(dev)	NULL

arch/ia64/sn/pci/pci_dma.c

@@ -34,7 +34,7 @@
  */
 static int sn_dma_supported(struct device *dev, u64 mask)
 {
-	BUG_ON(dev->bus != &pci_bus_type);
+	BUG_ON(!dev_is_pci(dev));
 
 	if (mask < 0x7fffffff)
 		return 0;
@@ -50,7 +50,7 @@ static int sn_dma_supported(struct device *dev, u64 mask)
  */
 int sn_dma_set_mask(struct device *dev, u64 dma_mask)
 {
-	BUG_ON(dev->bus != &pci_bus_type);
+	BUG_ON(!dev_is_pci(dev));
 
 	if (!sn_dma_supported(dev, dma_mask))
 		return 0;
@@ -85,7 +85,7 @@ static void *sn_dma_alloc_coherent(struct device *dev, size_t size,
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
 
-	BUG_ON(dev->bus != &pci_bus_type);
+	BUG_ON(!dev_is_pci(dev));
 
 	/*
 	 * Allocate the memory.
@@ -143,7 +143,7 @@ static void sn_dma_free_coherent(struct device *dev, size_t size, void *cpu_addr
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
 
-	BUG_ON(dev->bus != &pci_bus_type);
+	BUG_ON(!dev_is_pci(dev));
 
 	provider->dma_unmap(pdev, dma_handle, 0);
 	free_pages((unsigned long)cpu_addr, get_order(size));
@@ -187,7 +187,7 @@ static dma_addr_t sn_dma_map_page(struct device *dev, struct page *page,
 
 	dmabarr = dma_get_attr(DMA_ATTR_WRITE_BARRIER, attrs);
 
-	BUG_ON(dev->bus != &pci_bus_type);
+	BUG_ON(!dev_is_pci(dev));
 
 	phys_addr = __pa(cpu_addr);
 	if (dmabarr)
@@ -223,7 +223,7 @@ static void sn_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
 
-	BUG_ON(dev->bus != &pci_bus_type);
+	BUG_ON(!dev_is_pci(dev));
 
 	provider->dma_unmap(pdev, dma_addr, dir);
 }
@@ -247,7 +247,7 @@ static void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sgl,
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
 	struct scatterlist *sg;
 
-	BUG_ON(dev->bus != &pci_bus_type);
+	BUG_ON(!dev_is_pci(dev));
 
 	for_each_sg(sgl, sg, nhwentries, i) {
 		provider->dma_unmap(pdev, sg->dma_address, dir);
@@ -284,7 +284,7 @@ static int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl,
 
 	dmabarr = dma_get_attr(DMA_ATTR_WRITE_BARRIER, attrs);
 
-	BUG_ON(dev->bus != &pci_bus_type);
+	BUG_ON(!dev_is_pci(dev));
 
 	/*
 	 * Setup a DMA address for each entry in the scatterlist.
@@ -323,26 +323,26 @@ static int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl,
 static void sn_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
 				       size_t size, enum dma_data_direction dir)
 {
-	BUG_ON(dev->bus != &pci_bus_type);
+	BUG_ON(!dev_is_pci(dev));
 }
 
 static void sn_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
 					  size_t size,
 					  enum dma_data_direction dir)
 {
-	BUG_ON(dev->bus != &pci_bus_type);
+	BUG_ON(!dev_is_pci(dev));
 }
 
 static void sn_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 				   int nelems, enum dma_data_direction dir)
 {
-	BUG_ON(dev->bus != &pci_bus_type);
+	BUG_ON(!dev_is_pci(dev));
 }
 
 static void sn_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 				      int nelems, enum dma_data_direction dir)
 {
-	BUG_ON(dev->bus != &pci_bus_type);
+	BUG_ON(!dev_is_pci(dev));
 }
 
 static int sn_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)

arch/parisc/kernel/drivers.c

@@ -282,18 +282,6 @@ find_pa_parent_type(const struct parisc_device *padev, int type)
 	return NULL;
 }
 
-#ifdef CONFIG_PCI
-static inline int is_pci_dev(struct device *dev)
-{
-	return dev->bus == &pci_bus_type;
-}
-#else
-static inline int is_pci_dev(struct device *dev)
-{
-	return 0;
-}
-#endif
-
 /*
  * get_node_path fills in @path with the firmware path to the device.
  * Note that if @node is a parisc device, we don't fill in the 'mod' field.
@@ -306,7 +294,7 @@ static void get_node_path(struct device *dev, struct hardware_path *path)
 	int i = 5;
 	memset(&path->bc, -1, 6);
 
-	if (is_pci_dev(dev)) {
+	if (dev_is_pci(dev)) {
 		unsigned int devfn = to_pci_dev(dev)->devfn;
 		path->mod = PCI_FUNC(devfn);
 		path->bc[i--] = PCI_SLOT(devfn);
@@ -314,7 +302,7 @@ static void get_node_path(struct device *dev, struct hardware_path *path)
 	}
 
 	while (dev != &root) {
-		if (is_pci_dev(dev)) {
+		if (dev_is_pci(dev)) {
 			unsigned int devfn = to_pci_dev(dev)->devfn;
 			path->bc[i--] = PCI_SLOT(devfn) | (PCI_FUNC(devfn)<< 5);
 		} else if (dev->bus == &parisc_bus_type) {
@@ -695,7 +683,7 @@ static int check_parent(struct device * dev, void * data)
 		if (dev->bus == &parisc_bus_type) {
 			if (match_parisc_device(dev, d->index, d->modpath))
 				d->dev = dev;
-		} else if (is_pci_dev(dev)) {
+		} else if (dev_is_pci(dev)) {
 			if (match_pci_device(dev, d->index, d->modpath))
 				d->dev = dev;
 		} else if (dev->bus == NULL) {
@@ -753,7 +741,7 @@ struct device *hwpath_to_device(struct hardware_path *modpath)
 		if (!parent)
 			return NULL;
 	}
-	if (is_pci_dev(parent)) /* pci devices already parse MOD */
+	if (dev_is_pci(parent)) /* pci devices already parse MOD */
 		return parent;
 	else
 		return parse_tree_node(parent, 6, modpath);
@@ -772,7 +760,7 @@ void device_to_hwpath(struct device *dev, struct hardware_path *path)
 		padev = to_parisc_device(dev);
 		get_node_path(dev->parent, path);
 		path->mod = padev->hw_path;
-	} else if (is_pci_dev(dev)) {
+	} else if (dev_is_pci(dev)) {
 		get_node_path(dev, path);
 	}
 }

arch/powerpc/kernel/eeh_driver.c

@@ -369,7 +369,9 @@ static void *eeh_rmv_device(void *data, void *userdata)
 	edev->mode |= EEH_DEV_DISCONNECTED;
 	(*removed)++;
 
+	pci_lock_rescan_remove();
 	pci_stop_and_remove_bus_device(dev);
+	pci_unlock_rescan_remove();
 
 	return NULL;
 }
@@ -416,10 +418,13 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 * into pcibios_add_pci_devices().
 	 */
 	eeh_pe_state_mark(pe, EEH_PE_KEEP);
-	if (bus)
+	if (bus) {
+		pci_lock_rescan_remove();
 		pcibios_remove_pci_devices(bus);
-	else if (frozen_bus)
+		pci_unlock_rescan_remove();
+	} else if (frozen_bus) {
 		eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed);
+	}
 
 	/* Reset the pci controller. (Asserts RST#; resets config space).
 	 * Reconfigure bridges and devices. Don't try to bring the system
@@ -429,6 +434,8 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	if (rc)
 		return rc;
 
+	pci_lock_rescan_remove();
+
 	/* Restore PE */
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
@@ -462,6 +469,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	pe->tstamp = tstamp;
 	pe->freeze_count = cnt;
 
+	pci_unlock_rescan_remove();
 	return 0;
 }
 
@@ -618,8 +626,11 @@ perm_error:
 	eeh_pe_dev_traverse(pe, eeh_report_failure, NULL);
 
 	/* Shut down the device drivers for good. */
-	if (frozen_bus)
+	if (frozen_bus) {
+		pci_lock_rescan_remove();
 		pcibios_remove_pci_devices(frozen_bus);
+		pci_unlock_rescan_remove();
+	}
 }
 
 static void eeh_handle_special_event(void)
@@ -692,6 +703,7 @@ static void eeh_handle_special_event(void)
 	if (rc == 2 || rc == 1)
 		eeh_handle_normal_event(pe);
 	else {
+		pci_lock_rescan_remove();
 		list_for_each_entry_safe(hose, tmp,
 			&hose_list, list_node) {
 			phb_pe = eeh_phb_pe_get(hose);
@@ -703,6 +715,7 @@ static void eeh_handle_special_event(void)
 			eeh_pe_dev_traverse(pe, eeh_report_failure, NULL);
 			pcibios_remove_pci_devices(bus);
 		}
+		pci_unlock_rescan_remove();
 	}
 }
 

arch/powerpc/kernel/pci-common.c

@@ -835,7 +835,7 @@ static void pcibios_fixup_resources(struct pci_dev *dev)
 		 * at 0 as unset as well, except if PCI_PROBE_ONLY is also set
 		 * since in that case, we don't want to re-assign anything
 		 */
-		pcibios_resource_to_bus(dev, &reg, res);
+		pcibios_resource_to_bus(dev->bus, &reg, res);
 		if (pci_has_flag(PCI_REASSIGN_ALL_RSRC) ||
 		    (reg.start == 0 && !pci_has_flag(PCI_PROBE_ONLY))) {
 			/* Only print message if not re-assigning */
@@ -886,7 +886,7 @@ static int pcibios_uninitialized_bridge_resource(struct pci_bus *bus,
 
 	/* Job is a bit different between memory and IO */
 	if (res->flags & IORESOURCE_MEM) {
-		pcibios_resource_to_bus(dev, &region, res);
+		pcibios_resource_to_bus(dev->bus, &region, res);
 
 		/* If the BAR is non-0 then it's probably been initialized */
 		if (region.start != 0)

arch/powerpc/kernel/pci_of_scan.c

@@ -111,7 +111,7 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev)
 		res->name = pci_name(dev);
 		region.start = base;
 		region.end = base + size - 1;
-		pcibios_bus_to_resource(dev, res, &region);
+		pcibios_bus_to_resource(dev->bus, res, &region);
 	}
 }
 
@@ -280,7 +280,7 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 		res->flags = flags;
 		region.start = of_read_number(&ranges[1], 2);
 		region.end = region.start + size - 1;
-		pcibios_bus_to_resource(dev, res, &region);
+		pcibios_bus_to_resource(dev->bus, res, &region);
 	}
 	sprintf(bus->name, "PCI Bus %04x:%02x", pci_domain_nr(bus),
 		bus->number);

arch/s390/pci/pci.c

@@ -407,8 +407,8 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 	struct msi_msg msg;
 	int rc;
 
-	if (type != PCI_CAP_ID_MSIX && type != PCI_CAP_ID_MSI)
-		return -EINVAL;
+	if (type == PCI_CAP_ID_MSI && nvec > 1)
+		return 1;
 	msi_vecs = min(nvec, ZPCI_MSI_VEC_MAX);
 	msi_vecs = min_t(unsigned int, msi_vecs, CONFIG_PCI_NR_MSI);
 

arch/sparc/kernel/pci.c

@@ -392,7 +392,7 @@ static void apb_fake_ranges(struct pci_dev *dev,
 	res->flags = IORESOURCE_IO;
 	region.start = (first << 21);
 	region.end = (last << 21) + ((1 << 21) - 1);
-	pcibios_bus_to_resource(dev, res, &region);
+	pcibios_bus_to_resource(dev->bus, res, &region);
 
 	pci_read_config_byte(dev, APB_MEM_ADDRESS_MAP, &map);
 	apb_calc_first_last(map, &first, &last);
@@ -400,7 +400,7 @@ static void apb_fake_ranges(struct pci_dev *dev,
 	res->flags = IORESOURCE_MEM;
 	region.start = (first << 29);
 	region.end = (last << 29) + ((1 << 29) - 1);
-	pcibios_bus_to_resource(dev, res, &region);
+	pcibios_bus_to_resource(dev->bus, res, &region);
 }
 
 static void pci_of_scan_bus(struct pci_pbm_info *pbm,
@@ -491,7 +491,7 @@ static void of_scan_pci_bridge(struct pci_pbm_info *pbm,
 		res->flags = flags;
 		region.start = GET_64BIT(ranges, 1);
 		region.end = region.start + size - 1;
-		pcibios_bus_to_resource(dev, res, &region);
+		pcibios_bus_to_resource(dev->bus, res, &region);
 	}
 after_ranges:
 	sprintf(bus->name, "PCI Bus %04x:%02x", pci_domain_nr(bus),

arch/x86/include/asm/pci.h

@@ -104,7 +104,7 @@ extern void pci_iommu_alloc(void);
 struct msi_desc;
 int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
 void native_teardown_msi_irq(unsigned int irq);
-void native_restore_msi_irqs(struct pci_dev *dev, int irq);
+void native_restore_msi_irqs(struct pci_dev *dev);
 int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 		  unsigned int irq_base, unsigned int irq_offset);
 #else
@@ -125,7 +125,6 @@ int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 
 /* generic pci stuff */
 #include <asm-generic/pci.h>
-#define PCIBIOS_MAX_MEM_32 0xffffffff
 
 #ifdef CONFIG_NUMA
 /* Returns the node based on pci bus */

arch/x86/include/asm/x86_init.h

@@ -181,7 +181,7 @@ struct x86_msi_ops {
 			       u8 hpet_id);
 	void (*teardown_msi_irq)(unsigned int irq);
 	void (*teardown_msi_irqs)(struct pci_dev *dev);
-	void (*restore_msi_irqs)(struct pci_dev *dev, int irq);
+	void (*restore_msi_irqs)(struct pci_dev *dev);
 	int  (*setup_hpet_msi)(unsigned int irq, unsigned int id);
 	u32 (*msi_mask_irq)(struct msi_desc *desc, u32 mask, u32 flag);
 	u32 (*msix_mask_irq)(struct msi_desc *desc, u32 flag);

arch/x86/kernel/acpi/boot.c

@@ -1034,9 +1034,7 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
 
 	if (!acpi_ioapic)
 		return 0;
-	if (!dev)
-		return 0;
-	if (dev->bus != &pci_bus_type)
+	if (!dev || !dev_is_pci(dev))
 		return 0;
 
 	pdev = to_pci_dev(dev);