Merge tag 'for-3.8' of git://git.kernel.org/pub/scm/linux/kernel/git/…

…helgaas/pci

Pull PCI update from Bjorn Helgaas:
 "Host bridge hotplug:
   - Untangle _PRT from struct pci_bus (Bjorn Helgaas)
   - Request _OSC control before scanning root bus (Taku Izumi)
   - Assign resources when adding host bridge (Yinghai Lu)
   - Remove root bus when removing host bridge (Yinghai Lu)
   - Remove _PRT during hot remove (Yinghai Lu)

  SRIOV
    - Add sysfs knobs to control numVFs (Don Dutile)

  Power management
   - Notify devices when power resource turned on (Huang Ying)

  Bug fixes
   - Work around broken _SEG on HP xw9300 (Bjorn Helgaas)
   - Keep runtime PM enabled for unbound PCI devices (Huang Ying)
   - Fix Optimus dual-GPU runtime D3 suspend issue (Dave Airlie)
   - Fix xen frontend shutdown issue (David Vrabel)
   - Work around PLX PCI 9050 BAR alignment erratum (Ian Abbott)

  Miscellaneous
   - Add GPL license for drivers/pci/ioapic (Andrew Cooks)
   - Add standard PCI-X, PCIe ASPM register #defines (Bjorn Helgaas)
   - NumaChip remote PCI support (Daniel Blueman)
   - Fix PCIe Link Capabilities Supported Link Speed definition (Jingoo
     Han)
   - Convert dev_printk() to dev_info(), etc (Joe Perches)
   - Add support for non PCI BAR ROM data (Matthew Garrett)
   - Add x86 support for host bridge translation offset (Mike Yoknis)
   - Report success only when every driver supports AER (Vijay
     Pandarathil)"

Fix up trivial conflicts.

* tag 'for-3.8' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (48 commits)
  PCI: Use phys_addr_t for physical ROM address
  x86/PCI: Add NumaChip remote PCI support
  ath9k: Use standard #defines for PCIe Capability ASPM fields
  iwlwifi: Use standard #defines for PCIe Capability ASPM fields
  iwlwifi: collapse wrapper for pcie_capability_read_word()
  iwlegacy: Use standard #defines for PCIe Capability ASPM fields
  iwlegacy: collapse wrapper for pcie_capability_read_word()
  cxgb3: Use standard #defines for PCIe Capability ASPM fields
  PCI: Add standard PCIe Capability Link ASPM field names
  PCI/portdrv: Use PCI Express Capability accessors
  PCI: Use standard PCIe Capability Link register field names
  x86: Use PCI setup data
  PCI: Add support for non-BAR ROMs
  PCI: Add pcibios_add_device
  EFI: Stash ROMs if they're not in the PCI BAR
  PCI: Add and use standard PCI-X Capability register names
  PCI/PM: Keep runtime PM enabled for unbound PCI devices
  xen-pcifront: Handle backend CLOSED without CLOSING
  PCI: SRIOV control and status via sysfs (documentation)
  PCI/AER: Report success only when every device has AER-aware driver
  ...

Documentation/ABI/testing/sysfs-bus-pci

@@ -222,3 +222,37 @@ Description:
 		satisfied too.  Reading this attribute will show the current
 		value of d3cold_allowed bit.  Writing this attribute will set
 		the value of d3cold_allowed bit.
+
+What:		/sys/bus/pci/devices/.../sriov_totalvfs
+Date:		November 2012
+Contact:	Donald Dutile <[email protected]>
+Description:
+		This file appears when a physical PCIe device supports SR-IOV.
+		Userspace applications can read this file to determine the
+		maximum number of Virtual Functions (VFs) a PCIe physical
+		function (PF) can support. Typically, this is the value reported
+		in the PF's SR-IOV extended capability structure's TotalVFs
+		element.  Drivers have the ability at probe time to reduce the
+		value read from this file via the pci_sriov_set_totalvfs()
+		function.
+
+What:		/sys/bus/pci/devices/.../sriov_numvfs
+Date:		November 2012
+Contact:	Donald Dutile <[email protected]>
+Description:
+		This file appears when a physical PCIe device supports SR-IOV.
+		Userspace applications can read and write to this file to
+		determine and control the enablement or disablement of Virtual
+		Functions (VFs) on the physical function (PF). A read of this
+		file will return the number of VFs that are enabled on this PF.
+		A number written to this file will enable the specified
+		number of VFs. A userspace application would typically read the
+		file and check that the value is zero, and then write the number
+		of VFs that should be enabled on the PF; the value written
+		should be less than or equal to the value in the sriov_totalvfs
+		file. A userspace application wanting to disable the VFs would
+		write a zero to this file. The core ensures that valid values
+		are written to this file, and returns errors when values are not
+		valid.  For example, writing a 2 to this file when sriov_numvfs
+		is not 0 and not 2 already will return an error. Writing a 10
+		when the value of sriov_totalvfs is 8 will return an error.

Documentation/PCI/pci-iov-howto.txt

@@ -2,6 +2,9 @@
 		Copyright (C) 2009 Intel Corporation
 		    Yu Zhao <[email protected]>
 
+		Update: November 2012
+			-- sysfs-based SRIOV enable-/disable-ment
+		Donald Dutile <[email protected]>
 
 1. Overview
 
@@ -24,10 +27,21 @@ real existing PCI device.
 
 2.1 How can I enable SR-IOV capability
 
-The device driver (PF driver) will control the enabling and disabling
-of the capability via API provided by SR-IOV core. If the hardware
-has SR-IOV capability, loading its PF driver would enable it and all
-VFs associated with the PF.
+Multiple methods are available for SR-IOV enablement.
+In the first method, the device driver (PF driver) will control the
+enabling and disabling of the capability via API provided by SR-IOV core.
+If the hardware has SR-IOV capability, loading its PF driver would
+enable it and all VFs associated with the PF.  Some PF drivers require
+a module parameter to be set to determine the number of VFs to enable.
+In the second method, a write to the sysfs file sriov_numvfs will
+enable and disable the VFs associated with a PCIe PF.  This method
+enables per-PF, VF enable/disable values versus the first method,
+which applies to all PFs of the same device.  Additionally, the
+PCI SRIOV core support ensures that enable/disable operations are
+valid to reduce duplication in multiple drivers for the same
+checks, e.g., check numvfs == 0 if enabling VFs, ensure
+numvfs <= totalvfs.
+The second method is the recommended method for new/future VF devices.
 
 2.2 How can I use the Virtual Functions
 
@@ -40,13 +54,22 @@ requires device driver that is same as a normal PCI device's.
 3.1 SR-IOV API
 
 To enable SR-IOV capability:
+(a) For the first method, in the driver:
 	int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn);
 	'nr_virtfn' is number of VFs to be enabled.
+(b) For the second method, from sysfs:
+	echo 'nr_virtfn' > \
+        /sys/bus/pci/devices/<DOMAIN:BUS:DEVICE.FUNCTION>/sriov_numvfs
 
 To disable SR-IOV capability:
+(a) For the first method, in the driver:
 	void pci_disable_sriov(struct pci_dev *dev);
+(b) For the second method, from sysfs:
+	echo  0 > \
+        /sys/bus/pci/devices/<DOMAIN:BUS:DEVICE.FUNCTION>/sriov_numvfs
 
 To notify SR-IOV core of Virtual Function Migration:
+(a) In the driver:
 	irqreturn_t pci_sriov_migration(struct pci_dev *dev);
 
 3.2 Usage example
@@ -88,6 +111,22 @@ static void dev_shutdown(struct pci_dev *dev)
 	...
 }
 
+static int dev_sriov_configure(struct pci_dev *dev, int numvfs)
+{
+	if (numvfs > 0) {
+		...
+		pci_enable_sriov(dev, numvfs);
+		...
+		return numvfs;
+	}
+	if (numvfs == 0) {
+		....
+		pci_disable_sriov(dev);
+		...
+		return 0;
+	}
+}
+
 static struct pci_driver dev_driver = {
 	.name =		"SR-IOV Physical Function driver",
 	.id_table =	dev_id_table,
@@ -96,4 +135,5 @@ static struct pci_driver dev_driver = {
 	.suspend =	dev_suspend,
 	.resume =	dev_resume,
 	.shutdown =	dev_shutdown,
+	.sriov_configure = dev_sriov_configure,
 };

arch/x86/Kconfig

@@ -370,6 +370,7 @@ config X86_NUMACHIP
 	depends on NUMA
 	depends on SMP
 	depends on X86_X2APIC
+	depends on PCI_MMCONFIG
 	---help---
 	  Adds support for Numascale NumaChip large-SMP systems. Needed to
 	  enable more than ~168 cores.

arch/x86/boot/compressed/eboot.c

@@ -8,6 +8,7 @@
  * ----------------------------------------------------------------------- */
 
 #include <linux/efi.h>
+#include <linux/pci.h>
 #include <asm/efi.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
@@ -245,6 +246,121 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size)
 	*size = len;
 }
 
+static efi_status_t setup_efi_pci(struct boot_params *params)
+{
+	efi_pci_io_protocol *pci;
+	efi_status_t status;
+	void **pci_handle;
+	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+	unsigned long nr_pci, size = 0;
+	int i;
+	struct setup_data *data;
+
+	data = (struct setup_data *)params->hdr.setup_data;
+
+	while (data && data->next)
+		data = (struct setup_data *)data->next;
+
+	status = efi_call_phys5(sys_table->boottime->locate_handle,
+				EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+				NULL, &size, pci_handle);
+
+	if (status == EFI_BUFFER_TOO_SMALL) {
+		status = efi_call_phys3(sys_table->boottime->allocate_pool,
+					EFI_LOADER_DATA, size, &pci_handle);
+
+		if (status != EFI_SUCCESS)
+			return status;
+
+		status = efi_call_phys5(sys_table->boottime->locate_handle,
+					EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+					NULL, &size, pci_handle);
+	}
+
+	if (status != EFI_SUCCESS)
+		goto free_handle;
+
+	nr_pci = size / sizeof(void *);
+	for (i = 0; i < nr_pci; i++) {
+		void *h = pci_handle[i];
+		uint64_t attributes;
+		struct pci_setup_rom *rom;
+
+		status = efi_call_phys3(sys_table->boottime->handle_protocol,
+					h, &pci_proto, &pci);
+
+		if (status != EFI_SUCCESS)
+			continue;
+
+		if (!pci)
+			continue;
+
+		status = efi_call_phys4(pci->attributes, pci,
+					EfiPciIoAttributeOperationGet, 0,
+					&attributes);
+
+		if (status != EFI_SUCCESS)
+			continue;
+
+		if (!attributes & EFI_PCI_IO_ATTRIBUTE_EMBEDDED_ROM)
+			continue;
+
+		if (!pci->romimage || !pci->romsize)
+			continue;
+
+		size = pci->romsize + sizeof(*rom);
+
+		status = efi_call_phys3(sys_table->boottime->allocate_pool,
+				EFI_LOADER_DATA, size, &rom);
+
+		if (status != EFI_SUCCESS)
+			continue;
+
+		rom->data.type = SETUP_PCI;
+		rom->data.len = size - sizeof(struct setup_data);
+		rom->data.next = 0;
+		rom->pcilen = pci->romsize;
+
+		status = efi_call_phys5(pci->pci.read, pci,
+					EfiPciIoWidthUint16, PCI_VENDOR_ID,
+					1, &(rom->vendor));
+
+		if (status != EFI_SUCCESS)
+			goto free_struct;
+
+		status = efi_call_phys5(pci->pci.read, pci,
+					EfiPciIoWidthUint16, PCI_DEVICE_ID,
+					1, &(rom->devid));
+
+		if (status != EFI_SUCCESS)
+			goto free_struct;
+
+		status = efi_call_phys5(pci->get_location, pci,
+					&(rom->segment), &(rom->bus),
+					&(rom->device), &(rom->function));
+
+		if (status != EFI_SUCCESS)
+			goto free_struct;
+
+		memcpy(rom->romdata, pci->romimage, pci->romsize);
+
+		if (data)
+			data->next = (uint64_t)rom;
+		else
+			params->hdr.setup_data = (uint64_t)rom;
+
+		data = (struct setup_data *)rom;
+
+		continue;
+	free_struct:
+		efi_call_phys1(sys_table->boottime->free_pool, rom);
+	}
+
+free_handle:
+	efi_call_phys1(sys_table->boottime->free_pool, pci_handle);
+	return status;
+}
+
 /*
  * See if we have Graphics Output Protocol
  */
@@ -1028,6 +1144,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
 
 	setup_graphics(boot_params);
 
+	setup_efi_pci(boot_params);
+
 	status = efi_call_phys3(sys_table->boottime->allocate_pool,
 				EFI_LOADER_DATA, sizeof(*gdt),
 				(void **)&gdt);

arch/x86/include/asm/bootparam.h

@@ -13,6 +13,7 @@
 #define SETUP_NONE			0
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
+#define SETUP_PCI			3
 
 /* extensible setup data list node */
 struct setup_data {

arch/x86/include/asm/numachip/numachip.h

@@ -0,0 +1,19 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Numascale NumaConnect-specific header file
+ *
+ * Copyright (C) 2012 Numascale AS. All rights reserved.
+ *
+ * Send feedback to <[email protected]>
+ *
+ */
+
+#ifndef _ASM_X86_NUMACHIP_NUMACHIP_H
+#define _ASM_X86_NUMACHIP_NUMACHIP_H
+
+extern int __init pci_numachip_init(void);
+
+#endif /* _ASM_X86_NUMACHIP_NUMACHIP_H */

arch/x86/include/asm/pci.h

@@ -171,4 +171,16 @@ cpumask_of_pcibus(const struct pci_bus *bus)
 }
 #endif
 
+struct pci_setup_rom {
+	struct setup_data data;
+	uint16_t vendor;
+	uint16_t devid;
+	uint64_t pcilen;
+	unsigned long segment;
+	unsigned long bus;
+	unsigned long device;
+	unsigned long function;
+	uint8_t romdata[0];
+};
+
 #endif /* _ASM_X86_PCI_H */

arch/x86/kernel/apic/apic_numachip.c

@@ -22,6 +22,7 @@
 #include <linux/hardirq.h>
 #include <linux/delay.h>
 
+#include <asm/numachip/numachip.h>
 #include <asm/numachip/numachip_csr.h>
 #include <asm/smp.h>
 #include <asm/apic.h>
@@ -179,6 +180,7 @@ static int __init numachip_system_init(void)
 		return 0;
 
 	x86_cpuinit.fixup_cpu_id = fixup_cpu_id;
+	x86_init.pci.arch_init = pci_numachip_init;
 
 	map_csrs();
 

arch/x86/kernel/setup.c

@@ -143,11 +143,7 @@ int default_check_phys_apicid_present(int phys_apicid)
 }
 #endif
 
-#ifndef CONFIG_DEBUG_BOOT_PARAMS
-struct boot_params __initdata boot_params;
-#else
 struct boot_params boot_params;
-#endif
 
 /*
  * Machine setup..

arch/x86/pci/Makefile

@@ -16,6 +16,7 @@ obj-$(CONFIG_STA2X11)           += sta2x11-fixup.o
 obj-$(CONFIG_X86_VISWS)		+= visws.o
 
 obj-$(CONFIG_X86_NUMAQ)		+= numaq_32.o
+obj-$(CONFIG_X86_NUMACHIP)	+= numachip.o
 
 obj-$(CONFIG_X86_INTEL_MID)	+= mrst.o