Merge master.kernel.org:/pub/scm/linux/kernel/git/gregkh/pci-2.6

Documentation/kernel-parameters.txt

@@ -1030,6 +1030,10 @@ running once the system is up.
 		irqmask=0xMMMM		[IA-32] Set a bit mask of IRQs allowed to be assigned
 					automatically to PCI devices. You can make the kernel
 					exclude IRQs of your ISA cards this way.
+		pirqaddr=0xAAAAA	[IA-32] Specify the physical address
+					of the PIRQ table (normally generated
+					by the BIOS) if it is outside the
+					F0000h-100000h range.
 		lastbus=N		[IA-32] Scan all buses till bus #N. Can be useful
 					if the kernel is unable to find your secondary buses
 					and you want to tell it explicitly which ones they are.

arch/i386/kernel/acpi/boot.c

@@ -159,9 +159,15 @@ char *__acpi_map_table(unsigned long phys, unsigned long size)
 #endif
 
 #ifdef CONFIG_PCI_MMCONFIG
-static int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size)
+/* The physical address of the MMCONFIG aperture.  Set from ACPI tables. */
+struct acpi_table_mcfg_config *pci_mmcfg_config;
+int pci_mmcfg_config_num;
+
+int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size)
 {
 	struct acpi_table_mcfg *mcfg;
+	unsigned long i;
+	int config_size;
 
 	if (!phys_addr || !size)
 		return -EINVAL;
@@ -172,18 +178,38 @@ static int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size)
 		return -ENODEV;
 	}
 
-	if (mcfg->base_reserved) {
-		printk(KERN_ERR PREFIX "MMCONFIG not in low 4GB of memory\n");
+	/* how many config structures do we have */
+	pci_mmcfg_config_num = 0;
+	i = size - sizeof(struct acpi_table_mcfg);
+	while (i >= sizeof(struct acpi_table_mcfg_config)) {
+		++pci_mmcfg_config_num;
+		i -= sizeof(struct acpi_table_mcfg_config);
+	};
+	if (pci_mmcfg_config_num == 0) {
+		printk(KERN_ERR PREFIX "MMCONFIG has no entries\n");
 		return -ENODEV;
 	}
 
-	pci_mmcfg_base_addr = mcfg->base_address;
+	config_size = pci_mmcfg_config_num * sizeof(*pci_mmcfg_config);
+	pci_mmcfg_config = kmalloc(config_size, GFP_KERNEL);
+	if (!pci_mmcfg_config) {
+		printk(KERN_WARNING PREFIX
+		       "No memory for MCFG config tables\n");
+		return -ENOMEM;
+	}
+
+	memcpy(pci_mmcfg_config, &mcfg->config, config_size);
+	for (i = 0; i < pci_mmcfg_config_num; ++i) {
+		if (mcfg->config[i].base_reserved) {
+			printk(KERN_ERR PREFIX
+			       "MMCONFIG not in low 4GB of memory\n");
+			return -ENODEV;
+		}
+	}
 
 	return 0;
 }
-#else
-#define	acpi_parse_mcfg NULL
-#endif /* !CONFIG_PCI_MMCONFIG */
+#endif /* CONFIG_PCI_MMCONFIG */
 
 #ifdef CONFIG_X86_LOCAL_APIC
 static int __init
@@ -507,6 +533,22 @@ acpi_unmap_lsapic(int cpu)
 EXPORT_SYMBOL(acpi_unmap_lsapic);
 #endif /* CONFIG_ACPI_HOTPLUG_CPU */
 
+int
+acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
+{
+	/* TBD */
+	return -EINVAL;
+}
+EXPORT_SYMBOL(acpi_register_ioapic);
+
+int
+acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base)
+{
+	/* TBD */
+	return -EINVAL;
+}
+EXPORT_SYMBOL(acpi_unregister_ioapic);
+
 static unsigned long __init
 acpi_scan_rsdp (
 	unsigned long		start,
@@ -1123,7 +1165,6 @@ int __init acpi_boot_init(void)
 	acpi_process_madt();
 
 	acpi_table_parse(ACPI_HPET, acpi_parse_hpet);
-	acpi_table_parse(ACPI_MCFG, acpi_parse_mcfg);
 
 	return 0;
 }

arch/i386/pci/common.c

@@ -25,7 +25,8 @@ unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 |
 
 int pci_routeirq;
 int pcibios_last_bus = -1;
-struct pci_bus *pci_root_bus = NULL;
+unsigned long pirq_table_addr;
+struct pci_bus *pci_root_bus;
 struct pci_raw_ops *raw_pci_ops;
 
 static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *value)
@@ -133,7 +134,7 @@ struct pci_bus * __devinit pcibios_scan_root(int busnum)
 
 	printk("PCI: Probing PCI hardware (bus %02x)\n", busnum);
 
-	return pci_scan_bus(busnum, &pci_root_ops, NULL);
+	return pci_scan_bus_parented(NULL, busnum, &pci_root_ops, NULL);
 }
 
 extern u8 pci_cache_line_size;
@@ -188,6 +189,9 @@ char * __devinit  pcibios_setup(char *str)
 	} else if (!strcmp(str, "biosirq")) {
 		pci_probe |= PCI_BIOS_IRQ_SCAN;
 		return NULL;
+	} else if (!strncmp(str, "pirqaddr=", 9)) {
+		pirq_table_addr = simple_strtoul(str+9, NULL, 0);
+		return NULL;
 	}
 #endif
 #ifdef CONFIG_PCI_DIRECT

arch/i386/pci/irq.c

@@ -57,6 +57,35 @@ struct irq_router_handler {
 
 int (*pcibios_enable_irq)(struct pci_dev *dev) = NULL;
 
+/*
+ *  Check passed address for the PCI IRQ Routing Table signature
+ *  and perform checksum verification.
+ */
+
+static inline struct irq_routing_table * pirq_check_routing_table(u8 *addr)
+{
+	struct irq_routing_table *rt;
+	int i;
+	u8 sum;
+
+	rt = (struct irq_routing_table *) addr;
+	if (rt->signature != PIRQ_SIGNATURE ||
+	    rt->version != PIRQ_VERSION ||
+	    rt->size % 16 ||
+	    rt->size < sizeof(struct irq_routing_table))
+		return NULL;
+	sum = 0;
+	for (i=0; i < rt->size; i++)
+		sum += addr[i];
+	if (!sum) {
+		DBG("PCI: Interrupt Routing Table found at 0x%p\n", rt);
+		return rt;
+	}
+	return NULL;
+}
+
+
+
 /*
  *  Search 0xf0000 -- 0xfffff for the PCI IRQ Routing Table.
  */
@@ -65,23 +94,17 @@ static struct irq_routing_table * __init pirq_find_routing_table(void)
 {
 	u8 *addr;
 	struct irq_routing_table *rt;
-	int i;
-	u8 sum;
 
+	if (pirq_table_addr) {
+		rt = pirq_check_routing_table((u8 *) __va(pirq_table_addr));
+		if (rt)
+			return rt;
+		printk(KERN_WARNING "PCI: PIRQ table NOT found at pirqaddr\n");
+	}
 	for(addr = (u8 *) __va(0xf0000); addr < (u8 *) __va(0x100000); addr += 16) {
-		rt = (struct irq_routing_table *) addr;
-		if (rt->signature != PIRQ_SIGNATURE ||
-		    rt->version != PIRQ_VERSION ||
-		    rt->size % 16 ||
-		    rt->size < sizeof(struct irq_routing_table))
-			continue;
-		sum = 0;
-		for(i=0; i<rt->size; i++)
-			sum += addr[i];
-		if (!sum) {
-			DBG("PCI: Interrupt Routing Table found at 0x%p\n", rt);
+		rt = pirq_check_routing_table(addr);
+		if (rt)
 			return rt;
-		}
 	}
 	return NULL;
 }

arch/i386/pci/legacy.c

@@ -45,6 +45,8 @@ static int __init pci_legacy_init(void)
 
 	printk("PCI: Probing PCI hardware\n");
 	pci_root_bus = pcibios_scan_root(0);
+	if (pci_root_bus)
+		pci_bus_add_devices(pci_root_bus);
 
 	pcibios_fixup_peer_bridges();
 

arch/i386/pci/mmconfig.c

@@ -11,11 +11,9 @@
 
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/acpi.h>
 #include "pci.h"
 
-/* The physical address of the MMCONFIG aperture.  Set from ACPI tables. */
-u32 pci_mmcfg_base_addr;
-
 #define mmcfg_virt_addr ((void __iomem *) fix_to_virt(FIX_PCIE_MCFG))
 
 /* The base address of the last MMCONFIG device accessed */
@@ -24,10 +22,31 @@ static u32 mmcfg_last_accessed_device;
 /*
  * Functions for accessing PCI configuration space with MMCONFIG accesses
  */
-
-static inline void pci_exp_set_dev_base(int bus, int devfn)
+static u32 get_base_addr(unsigned int seg, int bus)
 {
-	u32 dev_base = pci_mmcfg_base_addr | (bus << 20) | (devfn << 12);
+	int cfg_num = -1;
+	struct acpi_table_mcfg_config *cfg;
+
+	while (1) {
+		++cfg_num;
+		if (cfg_num >= pci_mmcfg_config_num) {
+			/* something bad is going on, no cfg table is found. */
+			/* so we fall back to the old way we used to do this */
+			/* and just rely on the first entry to be correct. */
+			return pci_mmcfg_config[0].base_address;
+		}
+		cfg = &pci_mmcfg_config[cfg_num];
+		if (cfg->pci_segment_group_number != seg)
+			continue;
+		if ((cfg->start_bus_number <= bus) &&
+		    (cfg->end_bus_number >= bus))
+			return cfg->base_address;
+	}
+}
+
+static inline void pci_exp_set_dev_base(unsigned int seg, int bus, int devfn)
+{
+	u32 dev_base = get_base_addr(seg, bus) | (bus << 20) | (devfn << 12);
 	if (dev_base != mmcfg_last_accessed_device) {
 		mmcfg_last_accessed_device = dev_base;
 		set_fixmap_nocache(FIX_PCIE_MCFG, dev_base);
@@ -44,7 +63,7 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
 
 	spin_lock_irqsave(&pci_config_lock, flags);
 
-	pci_exp_set_dev_base(bus, devfn);
+	pci_exp_set_dev_base(seg, bus, devfn);
 
 	switch (len) {
 	case 1:
@@ -73,7 +92,7 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
 
 	spin_lock_irqsave(&pci_config_lock, flags);
 
-	pci_exp_set_dev_base(bus, devfn);
+	pci_exp_set_dev_base(seg, bus, devfn);
 
 	switch (len) {
 	case 1:
@@ -101,7 +120,11 @@ static int __init pci_mmcfg_init(void)
 {
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
 		goto out;
-	if (!pci_mmcfg_base_addr)
+
+	acpi_table_parse(ACPI_MCFG, acpi_parse_mcfg);
+	if ((pci_mmcfg_config_num == 0) ||
+	    (pci_mmcfg_config == NULL) ||
+	    (pci_mmcfg_config[0].base_address == 0))
 		goto out;
 
 	/* Kludge for now. Don't use mmconfig on AMD systems because

arch/i386/pci/numa.c

@@ -115,6 +115,8 @@ static int __init pci_numa_init(void)
 		return 0;
 
 	pci_root_bus = pcibios_scan_root(0);
+	if (pci_root_bus)
+		pci_bus_add_devices(pci_root_bus);
 	if (num_online_nodes() > 1)
 		for_each_online_node(quad) {
 			if (quad == 0)

arch/i386/pci/pci.h

@@ -27,6 +27,7 @@
 #define PCI_ASSIGN_ALL_BUSSES	0x4000
 
 extern unsigned int pci_probe;
+extern unsigned long pirq_table_addr;
 
 /* pci-i386.c */
 

arch/ia64/kernel/acpi.c

@@ -236,9 +236,7 @@ acpi_parse_iosapic (acpi_table_entry_header *header, const unsigned long end)
 	if (BAD_MADT_ENTRY(iosapic, end))
 		return -EINVAL;
 
-	iosapic_init(iosapic->address, iosapic->global_irq_base);
-
-	return 0;
+	return iosapic_init(iosapic->address, iosapic->global_irq_base);
 }
 
 
@@ -772,7 +770,7 @@ EXPORT_SYMBOL(acpi_unmap_lsapic);
  
 
 #ifdef CONFIG_ACPI_NUMA
-acpi_status __init
+acpi_status __devinit
 acpi_map_iosapic (acpi_handle handle, u32 depth, void *context, void **ret)
 {
 	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
@@ -825,4 +823,28 @@ acpi_map_iosapic (acpi_handle handle, u32 depth, void *context, void **ret)
 	return AE_OK;
 }
 #endif /* CONFIG_NUMA */
+
+int
+acpi_register_ioapic (acpi_handle handle, u64 phys_addr, u32 gsi_base)
+{
+	int err;
+
+	if ((err = iosapic_init(phys_addr, gsi_base)))
+		return err;
+
+#if CONFIG_ACPI_NUMA
+	acpi_map_iosapic(handle, 0, NULL, NULL);
+#endif /* CONFIG_ACPI_NUMA */
+
+	return 0;
+}
+EXPORT_SYMBOL(acpi_register_ioapic);
+
+int
+acpi_unregister_ioapic (acpi_handle handle, u32 gsi_base)
+{
+	return iosapic_remove(gsi_base);
+}
+EXPORT_SYMBOL(acpi_unregister_ioapic);
+
 #endif /* CONFIG_ACPI_BOOT */

arch/ia64/kernel/iosapic.c

@@ -129,14 +129,13 @@ static struct iosapic {
 	char __iomem	*addr;		/* base address of IOSAPIC */
 	unsigned int 	gsi_base;	/* first GSI assigned to this IOSAPIC */
 	unsigned short 	num_rte;	/* number of RTE in this IOSAPIC */
+	int		rtes_inuse;	/* # of RTEs in use on this IOSAPIC */
 #ifdef CONFIG_NUMA
 	unsigned short	node;		/* numa node association via pxm */
 #endif
 } iosapic_lists[NR_IOSAPICS];
 
-static int num_iosapic;
-
-static unsigned char pcat_compat __initdata;	/* 8259 compatibility flag */
+static unsigned char pcat_compat __devinitdata;	/* 8259 compatibility flag */
 
 static int iosapic_kmalloc_ok;
 static LIST_HEAD(free_rte_list);
@@ -149,7 +148,7 @@ find_iosapic (unsigned int gsi)
 {
 	int i;
 
-	for (i = 0; i < num_iosapic; i++) {
+	for (i = 0; i < NR_IOSAPICS; i++) {
 		if ((unsigned) (gsi - iosapic_lists[i].gsi_base) < iosapic_lists[i].num_rte)
 			return i;
 	}
@@ -598,6 +597,7 @@ register_intr (unsigned int gsi, int vector, unsigned char delivery,
 		rte->refcnt++;
 		list_add_tail(&rte->rte_list, &iosapic_intr_info[vector].rtes);
 		iosapic_intr_info[vector].count++;
+		iosapic_lists[index].rtes_inuse++;
 	}
 	else if (vector_is_shared(vector)) {
 		struct iosapic_intr_info *info = &iosapic_intr_info[vector];
@@ -778,7 +778,7 @@ void
 iosapic_unregister_intr (unsigned int gsi)
 {
 	unsigned long flags;
-	int irq, vector;
+	int irq, vector, index;
 	irq_desc_t *idesc;
 	u32 low32;
 	unsigned long trigger, polarity;
@@ -819,6 +819,9 @@ iosapic_unregister_intr (unsigned int gsi)
 		list_del(&rte->rte_list);
 		iosapic_intr_info[vector].count--;
 		iosapic_free_rte(rte);
+		index = find_iosapic(gsi);
+		iosapic_lists[index].rtes_inuse--;
+		WARN_ON(iosapic_lists[index].rtes_inuse < 0);
 
 		trigger	 = iosapic_intr_info[vector].trigger;
 		polarity = iosapic_intr_info[vector].polarity;
@@ -952,30 +955,86 @@ iosapic_system_init (int system_pcat_compat)
 	}
 }
 
-void __init
+static inline int
+iosapic_alloc (void)
+{
+	int index;
+
+	for (index = 0; index < NR_IOSAPICS; index++)
+		if (!iosapic_lists[index].addr)
+			return index;
+
+	printk(KERN_WARNING "%s: failed to allocate iosapic\n", __FUNCTION__);
+	return -1;
+}
+
+static inline void
+iosapic_free (int index)
+{
+	memset(&iosapic_lists[index], 0, sizeof(iosapic_lists[0]));
+}
+
+static inline int
+iosapic_check_gsi_range (unsigned int gsi_base, unsigned int ver)
+{
+	int index;
+	unsigned int gsi_end, base, end;
+
+	/* check gsi range */
+	gsi_end = gsi_base + ((ver >> 16) & 0xff);
+	for (index = 0; index < NR_IOSAPICS; index++) {
+		if (!iosapic_lists[index].addr)
+			continue;
+
+		base = iosapic_lists[index].gsi_base;
+		end  = base + iosapic_lists[index].num_rte - 1;
+
+		if (gsi_base < base && gsi_end < base)
+			continue;/* OK */
+
+		if (gsi_base > end && gsi_end > end)
+			continue; /* OK */
+
+		return -EBUSY;
+	}
+	return 0;
+}
+
+int __devinit
 iosapic_init (unsigned long phys_addr, unsigned int gsi_base)
 {
-	int num_rte;
+	int num_rte, err, index;
 	unsigned int isa_irq, ver;
 	char __iomem *addr;
+	unsigned long flags;
 
-	addr = ioremap(phys_addr, 0);
-	ver = iosapic_version(addr);
+	spin_lock_irqsave(&iosapic_lock, flags);
+	{
+		addr = ioremap(phys_addr, 0);
+		ver = iosapic_version(addr);
 
-	/*
-	 * The MAX_REDIR register holds the highest input pin
-	 * number (starting from 0).
-	 * We add 1 so that we can use it for number of pins (= RTEs)
-	 */
-	num_rte = ((ver >> 16) & 0xff) + 1;
+		if ((err = iosapic_check_gsi_range(gsi_base, ver))) {
+			iounmap(addr);
+			spin_unlock_irqrestore(&iosapic_lock, flags);
+			return err;
+		}
 
-	iosapic_lists[num_iosapic].addr = addr;
-	iosapic_lists[num_iosapic].gsi_base = gsi_base;
-	iosapic_lists[num_iosapic].num_rte = num_rte;
+		/*
+		 * The MAX_REDIR register holds the highest input pin
+		 * number (starting from 0).
+		 * We add 1 so that we can use it for number of pins (= RTEs)
+		 */
+		num_rte = ((ver >> 16) & 0xff) + 1;
+
+		index = iosapic_alloc();
+		iosapic_lists[index].addr = addr;
+		iosapic_lists[index].gsi_base = gsi_base;
+		iosapic_lists[index].num_rte = num_rte;
 #ifdef CONFIG_NUMA
-	iosapic_lists[num_iosapic].node = MAX_NUMNODES;
+		iosapic_lists[index].node = MAX_NUMNODES;
 #endif
-	num_iosapic++;
+	}
+	spin_unlock_irqrestore(&iosapic_lock, flags);
 
 	if ((gsi_base == 0) && pcat_compat) {
 		/*
@@ -986,10 +1045,43 @@ iosapic_init (unsigned long phys_addr, unsigned int gsi_base)
 		for (isa_irq = 0; isa_irq < 16; ++isa_irq)
 			iosapic_override_isa_irq(isa_irq, isa_irq, IOSAPIC_POL_HIGH, IOSAPIC_EDGE);
 	}
+	return 0;
 }
 
+#ifdef CONFIG_HOTPLUG
+int
+iosapic_remove (unsigned int gsi_base)
+{
+	int index, err = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iosapic_lock, flags);
+	{
+		index = find_iosapic(gsi_base);
+		if (index < 0) {
+			printk(KERN_WARNING "%s: No IOSAPIC for GSI base %u\n",
+			       __FUNCTION__, gsi_base);
+			goto out;
+		}
+
+		if (iosapic_lists[index].rtes_inuse) {
+			err = -EBUSY;
+			printk(KERN_WARNING "%s: IOSAPIC for GSI base %u is busy\n",
+			       __FUNCTION__, gsi_base);
+			goto out;
+		}
+
+		iounmap(iosapic_lists[index].addr);
+		iosapic_free(index);
+	}
+ out:
+	spin_unlock_irqrestore(&iosapic_lock, flags);
+	return err;
+}
+#endif /* CONFIG_HOTPLUG */
+
 #ifdef CONFIG_NUMA
-void __init
+void __devinit
 map_iosapic_to_node(unsigned int gsi_base, int node)
 {
 	int index;

arch/ia64/pci/pci.c

@@ -312,7 +312,7 @@ pci_acpi_scan_root(struct acpi_device *device, int domain, int bus)
 	acpi_walk_resources(device->handle, METHOD_NAME__CRS, add_window,
 			&info);
 
-	pbus = pci_scan_bus(bus, &pci_root_ops, controller);
+	pbus = pci_scan_bus_parented(NULL, bus, &pci_root_ops, controller);
 	if (pbus)
 		pcibios_setup_root_windows(pbus, controller);
 
@@ -373,6 +373,25 @@ void pcibios_bus_to_resource(struct pci_dev *dev,
 	res->end = region->end + offset;
 }
 
+static int __devinit is_valid_resource(struct pci_dev *dev, int idx)
+{
+	unsigned int i, type_mask = IORESOURCE_IO | IORESOURCE_MEM;
+	struct resource *devr = &dev->resource[idx];
+
+	if (!dev->bus)
+		return 0;
+	for (i=0; i<PCI_BUS_NUM_RESOURCES; i++) {
+		struct resource *busr = dev->bus->resource[i];
+
+		if (!busr || ((busr->flags ^ devr->flags) & type_mask))
+			continue;
+		if ((devr->start) && (devr->start >= busr->start) &&
+				(devr->end <= busr->end))
+			return 1;
+	}
+	return 0;
+}
+
 static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev)
 {
 	struct pci_bus_region region;
@@ -386,7 +405,8 @@ static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev)
 		region.start = dev->resource[i].start;
 		region.end = dev->resource[i].end;
 		pcibios_bus_to_resource(dev, &dev->resource[i], &region);
-		pci_claim_resource(dev, i);
+		if ((is_valid_resource(dev, i)))
+			pci_claim_resource(dev, i);
 	}
 }
 
@@ -398,6 +418,10 @@ pcibios_fixup_bus (struct pci_bus *b)
 {
 	struct pci_dev *dev;
 
+	if (b->self) {
+		pci_read_bridge_bases(b);
+		pcibios_fixup_device_resources(b->self);
+	}
 	list_for_each_entry(dev, &b->devices, bus_list)
 		pcibios_fixup_device_resources(dev);
 
@@ -418,18 +442,24 @@ pcibios_enable_resources (struct pci_dev *dev, int mask)
 	u16 cmd, old_cmd;
 	int idx;
 	struct resource *r;
+	unsigned long type_mask = IORESOURCE_IO | IORESOURCE_MEM;
 
 	if (!dev)
 		return -EINVAL;
 
 	pci_read_config_word(dev, PCI_COMMAND, &cmd);
 	old_cmd = cmd;
-	for (idx=0; idx<6; idx++) {
+	for (idx=0; idx<PCI_NUM_RESOURCES; idx++) {
 		/* Only set up the desired resources.  */
 		if (!(mask & (1 << idx)))
 			continue;
 
 		r = &dev->resource[idx];
+		if (!(r->flags & type_mask))
+			continue;
+		if ((idx == PCI_ROM_RESOURCE) &&
+				(!(r->flags & IORESOURCE_ROM_ENABLE)))
+			continue;
 		if (!r->start && r->end) {
 			printk(KERN_ERR
 			       "PCI: Device %s not available because of resource collisions\n",
@@ -441,8 +471,6 @@ pcibios_enable_resources (struct pci_dev *dev, int mask)
 		if (r->flags & IORESOURCE_MEM)
 			cmd |= PCI_COMMAND_MEMORY;
 	}
-	if (dev->resource[PCI_ROM_RESOURCE].start)
-		cmd |= PCI_COMMAND_MEMORY;
 	if (cmd != old_cmd) {
 		printk("PCI: Enabling device %s (%04x -> %04x)\n", pci_name(dev), old_cmd, cmd);
 		pci_write_config_word(dev, PCI_COMMAND, cmd);

arch/ppc/kernel/pci.c

@@ -1495,7 +1495,7 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 		*offset += hose->pci_mem_offset;
 		res_bit = IORESOURCE_MEM;
 	} else {
-		io_offset = (unsigned long)hose->io_base_virt;
+		io_offset = hose->io_base_virt - ___IO_BASE;
 		*offset += io_offset;
 		res_bit = IORESOURCE_IO;
 	}
@@ -1522,7 +1522,7 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 
 		/* found it! construct the final physical address */
 		if (mmap_state == pci_mmap_io)
-			*offset += hose->io_base_phys - _IO_BASE;
+			*offset += hose->io_base_phys - io_offset;
 		return rp;
 	}
 
@@ -1739,6 +1739,23 @@ long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn)
 	return result;
 }
 
+void pci_resource_to_user(const struct pci_dev *dev, int bar,
+			  const struct resource *rsrc,
+			  u64 *start, u64 *end)
+{
+	struct pci_controller *hose = pci_bus_to_hose(dev->bus->number);
+	unsigned long offset = 0;
+
+	if (hose == NULL)
+		return;
+
+	if (rsrc->flags & IORESOURCE_IO)
+		offset = ___IO_BASE - hose->io_base_virt + hose->io_base_phys;
+
+	*start = rsrc->start + offset;
+	*end = rsrc->end + offset;
+}
+
 void __init
 pci_init_resource(struct resource *res, unsigned long start, unsigned long end,
 		  int flags, char *name)

arch/ppc64/kernel/pci.c

@@ -351,7 +351,7 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 		*offset += hose->pci_mem_offset;
 		res_bit = IORESOURCE_MEM;
 	} else {
-		io_offset = (unsigned long)hose->io_base_virt;
+		io_offset = (unsigned long)hose->io_base_virt - pci_io_base;
 		*offset += io_offset;
 		res_bit = IORESOURCE_IO;
 	}
@@ -378,7 +378,7 @@ static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
 
 		/* found it! construct the final physical address */
 		if (mmap_state == pci_mmap_io)
-			*offset += hose->io_base_phys - io_offset;
+		       	*offset += hose->io_base_phys - io_offset;
 		return rp;
 	}
 
@@ -944,4 +944,22 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
 }
 EXPORT_SYMBOL(pci_read_irq_line);
 
+void pci_resource_to_user(const struct pci_dev *dev, int bar,
+			  const struct resource *rsrc,
+			  u64 *start, u64 *end)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	unsigned long offset = 0;
+
+	if (hose == NULL)
+		return;
+
+	if (rsrc->flags & IORESOURCE_IO)
+		offset = pci_io_base - (unsigned long)hose->io_base_virt +
+			hose->io_base_phys;
+
+	*start = rsrc->start + offset;
+	*end = rsrc->end + offset;
+}
+
 #endif /* CONFIG_PPC_MULTIPLATFORM */

arch/x86_64/pci/mmconfig.c

@@ -7,25 +7,50 @@
 
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/acpi.h>
 #include "pci.h"
 
 #define MMCONFIG_APER_SIZE (256*1024*1024)
 
-/* The physical address of the MMCONFIG aperture.  Set from ACPI tables. */
-u32 pci_mmcfg_base_addr;
-
 /* Static virtual mapping of the MMCONFIG aperture */
-char *pci_mmcfg_virt;
+struct mmcfg_virt {
+	struct acpi_table_mcfg_config *cfg;
+	char *virt;
+};
+static struct mmcfg_virt *pci_mmcfg_virt;
 
-static inline char *pci_dev_base(unsigned int bus, unsigned int devfn)
+static char *get_virt(unsigned int seg, int bus)
 {
-	return pci_mmcfg_virt + ((bus << 20) | (devfn << 12));
+	int cfg_num = -1;
+	struct acpi_table_mcfg_config *cfg;
+
+	while (1) {
+		++cfg_num;
+		if (cfg_num >= pci_mmcfg_config_num) {
+			/* something bad is going on, no cfg table is found. */
+			/* so we fall back to the old way we used to do this */
+			/* and just rely on the first entry to be correct. */
+			return pci_mmcfg_virt[0].virt;
+		}
+		cfg = pci_mmcfg_virt[cfg_num].cfg;
+		if (cfg->pci_segment_group_number != seg)
+			continue;
+		if ((cfg->start_bus_number <= bus) &&
+		    (cfg->end_bus_number >= bus))
+			return pci_mmcfg_virt[cfg_num].virt;
+	}
+}
+
+static inline char *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn)
+{
+
+	return get_virt(seg, bus) + ((bus << 20) | (devfn << 12));
 }
 
 static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
 			  unsigned int devfn, int reg, int len, u32 *value)
 {
-	char *addr = pci_dev_base(bus, devfn); 
+	char *addr = pci_dev_base(seg, bus, devfn);
 
 	if (unlikely(!value || (bus > 255) || (devfn > 255) || (reg > 4095)))
 		return -EINVAL;
@@ -48,7 +73,7 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
 static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
 			   unsigned int devfn, int reg, int len, u32 value)
 {
-	char *addr = pci_dev_base(bus,devfn);
+	char *addr = pci_dev_base(seg, bus, devfn);
 
 	if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095)))
 		return -EINVAL;
@@ -75,9 +100,15 @@ static struct pci_raw_ops pci_mmcfg = {
 
 static int __init pci_mmcfg_init(void)
 {
+	int i;
+
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
 		return 0;
-	if (!pci_mmcfg_base_addr)
+
+	acpi_table_parse(ACPI_MCFG, acpi_parse_mcfg);
+	if ((pci_mmcfg_config_num == 0) ||
+	    (pci_mmcfg_config == NULL) ||
+	    (pci_mmcfg_config[0].base_address == 0))
 		return 0;
 
 	/* Kludge for now. Don't use mmconfig on AMD systems because
@@ -88,13 +119,22 @@ static int __init pci_mmcfg_init(void)
 		return 0; 
 
 	/* RED-PEN i386 doesn't do _nocache right now */
-	pci_mmcfg_virt = ioremap_nocache(pci_mmcfg_base_addr, MMCONFIG_APER_SIZE);
-	if (!pci_mmcfg_virt) { 
-		printk("PCI: Cannot map mmconfig aperture\n");
+	pci_mmcfg_virt = kmalloc(sizeof(*pci_mmcfg_virt) * pci_mmcfg_config_num, GFP_KERNEL);
+	if (pci_mmcfg_virt == NULL) {
+		printk("PCI: Can not allocate memory for mmconfig structures\n");
 		return 0;
 	}
+	for (i = 0; i < pci_mmcfg_config_num; ++i) {
+		pci_mmcfg_virt[i].cfg = &pci_mmcfg_config[i];
+		pci_mmcfg_virt[i].virt = ioremap_nocache(pci_mmcfg_config[i].base_address, MMCONFIG_APER_SIZE);
+		if (!pci_mmcfg_virt[i].virt) {
+			printk("PCI: Cannot map mmconfig aperture for segment %d\n",
+			       pci_mmcfg_config[i].pci_segment_group_number);
+			return 0;
+		}
+		printk(KERN_INFO "PCI: Using MMCONFIG at %x\n", pci_mmcfg_config[i].base_address);
+	}
 
-	printk(KERN_INFO "PCI: Using MMCONFIG at %x\n", pci_mmcfg_base_addr);
 	raw_pci_ops = &pci_mmcfg;
 	pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;
 

drivers/acpi/container.c

@@ -153,7 +153,7 @@ container_device_add(struct acpi_device **device, acpi_handle handle)
 		return_VALUE(-ENODEV);
 	}
 
-	result = acpi_bus_scan(*device);
+	result = acpi_bus_start(*device);
 
 	return_VALUE(result);
 }

drivers/acpi/pci_bind.c

@@ -61,15 +61,14 @@ acpi_pci_data_handler (
 
 
 /**
- * acpi_os_get_pci_id
+ * acpi_get_pci_id
  * ------------------
  * This function is used by the ACPI Interpreter (a.k.a. Core Subsystem)
  * to resolve PCI information for ACPI-PCI devices defined in the namespace.
  * This typically occurs when resolving PCI operation region information.
  */
-#ifdef ACPI_FUTURE_USAGE
 acpi_status
-acpi_os_get_pci_id (
+acpi_get_pci_id (
 	acpi_handle		handle,
 	struct acpi_pci_id	*id)
 {
@@ -78,7 +77,7 @@ acpi_os_get_pci_id (
 	struct acpi_device	*device = NULL;
 	struct acpi_pci_data	*data = NULL;
 
-	ACPI_FUNCTION_TRACE("acpi_os_get_pci_id");
+	ACPI_FUNCTION_TRACE("acpi_get_pci_id");
 
 	if (!id)
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
@@ -92,7 +91,7 @@ acpi_os_get_pci_id (
 	}
 
 	status = acpi_get_data(handle, acpi_pci_data_handler, (void**) &data);
-	if (ACPI_FAILURE(status) || !data || !data->dev) {
+	if (ACPI_FAILURE(status) || !data) {
 		ACPI_DEBUG_PRINT((ACPI_DB_ERROR, 
 			"Invalid ACPI-PCI context for device %s\n",
 			acpi_device_bid(device)));
@@ -115,7 +114,7 @@ acpi_os_get_pci_id (
 
 	return_ACPI_STATUS(AE_OK);
 }
-#endif  /*  ACPI_FUTURE_USAGE  */
+EXPORT_SYMBOL(acpi_get_pci_id);
 
 	
 int
@@ -129,6 +128,8 @@ acpi_pci_bind (
 	char			*pathname = NULL;
 	struct acpi_buffer	buffer = {0, NULL};
 	acpi_handle		handle = NULL;
+	struct pci_dev		*dev;
+	struct pci_bus 		*bus;
 
 	ACPI_FUNCTION_TRACE("acpi_pci_bind");
 
@@ -193,8 +194,20 @@ acpi_pci_bind (
 	 * Locate matching device in PCI namespace.  If it doesn't exist
 	 * this typically means that the device isn't currently inserted
 	 * (e.g. docking station, port replicator, etc.).
+	 * We cannot simply search the global pci device list, since
+	 * PCI devices are added to the global pci list when the root
+	 * bridge start ops are run, which may not have happened yet.
 	 */
-	data->dev = pci_find_slot(data->id.bus, PCI_DEVFN(data->id.device, data->id.function));
+	bus = pci_find_bus(data->id.segment, data->id.bus);
+	if (bus) {
+		list_for_each_entry(dev, &bus->devices, bus_list) {
+			if (dev->devfn == PCI_DEVFN(data->id.device,
+						data->id.function)) {
+				data->dev = dev;
+				break;
+			}
+		}
+	}
 	if (!data->dev) {
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO, 
 			"Device %02x:%02x:%02x.%02x not present in PCI namespace\n",

drivers/acpi/pci_root.c

@@ -46,6 +46,7 @@ ACPI_MODULE_NAME		("pci_root")
 
 static int acpi_pci_root_add (struct acpi_device *device);
 static int acpi_pci_root_remove (struct acpi_device *device, int type);
+static int acpi_pci_root_start (struct acpi_device *device);
 
 static struct acpi_driver acpi_pci_root_driver = {
 	.name =		ACPI_PCI_ROOT_DRIVER_NAME,
@@ -54,6 +55,7 @@ static struct acpi_driver acpi_pci_root_driver = {
 	.ops =		{
 				.add =    acpi_pci_root_add,
 				.remove = acpi_pci_root_remove,
+				.start =  acpi_pci_root_start,
 			},
 };
 
@@ -169,6 +171,7 @@ acpi_pci_root_add (
 	if (!root)
 		return_VALUE(-ENOMEM);
 	memset(root, 0, sizeof(struct acpi_pci_root));
+	INIT_LIST_HEAD(&root->node);
 
 	root->handle = device->handle;
 	strcpy(acpi_device_name(device), ACPI_PCI_ROOT_DEVICE_NAME);
@@ -298,12 +301,31 @@ acpi_pci_root_add (
 			root->id.bus);
 
 end:
-	if (result)
+	if (result) {
+		if (!list_empty(&root->node))
+			list_del(&root->node);
 		kfree(root);
+	}
 
 	return_VALUE(result);
 }
 
+static int
+acpi_pci_root_start (
+	struct acpi_device	*device)
+{
+	struct acpi_pci_root	*root;
+
+	ACPI_FUNCTION_TRACE("acpi_pci_root_start");
+
+	list_for_each_entry(root, &acpi_pci_roots, node) {
+		if (root->handle == device->handle) {
+			pci_bus_add_devices(root->bus);
+			return_VALUE(0);
+		}
+	}
+	return_VALUE(-ENODEV);
+}
 
 static int
 acpi_pci_root_remove (

drivers/acpi/processor_core.c

@@ -723,7 +723,7 @@ int acpi_processor_device_add(
 		return_VALUE(-ENODEV);
 	}
 
-	acpi_bus_scan(*device);
+	acpi_bus_start(*device);
 
 	pr = acpi_driver_data(*device);
 	if (!pr)

drivers/acpi/scan.c

@@ -553,20 +553,29 @@ acpi_bus_driver_init (
 	 * upon possible configuration and currently allocated resources.
 	 */
 
+	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Driver successfully bound to device\n"));
+	return_VALUE(0);
+}
+
+int
+acpi_start_single_object (
+		struct acpi_device *device)
+{
+	int result = 0;
+	struct acpi_driver *driver;
+
+	ACPI_FUNCTION_TRACE("acpi_start_single_object");
+
+	if (!(driver = device->driver))
+		return_VALUE(0);
+
 	if (driver->ops.start) {
 		result = driver->ops.start(device);
 		if (result && driver->ops.remove)
 			driver->ops.remove(device, ACPI_BUS_REMOVAL_NORMAL);
-		return_VALUE(result);
 	}
 
-	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Driver successfully bound to device\n"));
-
-	if (driver->ops.scan) {
-		driver->ops.scan(device);
-	}
-
-	return_VALUE(0);
+	return_VALUE(result);
 }
 
 static int acpi_driver_attach(struct acpi_driver * drv)
@@ -586,6 +595,7 @@ static int acpi_driver_attach(struct acpi_driver * drv)
 
 		if (!acpi_bus_match(dev, drv)) {
 			if (!acpi_bus_driver_init(dev, drv)) {
+				acpi_start_single_object(dev);
 				atomic_inc(&drv->references);
 				count++;
 				ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found driver [%s] for device [%s]\n",
@@ -1009,8 +1019,8 @@ acpi_bus_remove (
 }
 
 
-int
-acpi_bus_add (
+static int
+acpi_add_single_object (
 	struct acpi_device	**child,
 	struct acpi_device	*parent,
 	acpi_handle		handle,
@@ -1019,7 +1029,7 @@ acpi_bus_add (
 	int			result = 0;
 	struct acpi_device	*device = NULL;
 
-	ACPI_FUNCTION_TRACE("acpi_bus_add");
+	ACPI_FUNCTION_TRACE("acpi_add_single_object");
 
 	if (!child)
 		return_VALUE(-EINVAL);
@@ -1140,7 +1150,7 @@ acpi_bus_add (
 	 *
 	 * TBD: Assumes LDM provides driver hot-plug capability.
 	 */
-	acpi_bus_find_driver(device);
+	result = acpi_bus_find_driver(device);
 
 end:
 	if (!result)
@@ -1153,10 +1163,10 @@ end:
 
 	return_VALUE(result);
 }
-EXPORT_SYMBOL(acpi_bus_add);
 
 
-int acpi_bus_scan (struct acpi_device	*start)
+static int acpi_bus_scan (struct acpi_device	*start,
+		struct acpi_bus_ops *ops)
 {
 	acpi_status		status = AE_OK;
 	struct acpi_device	*parent = NULL;
@@ -1229,9 +1239,20 @@ int acpi_bus_scan (struct acpi_device	*start)
 			continue;
 		}
 
-		status = acpi_bus_add(&child, parent, chandle, type);
-		if (ACPI_FAILURE(status))
-			continue;
+		if (ops->acpi_op_add)
+			status = acpi_add_single_object(&child, parent,
+					chandle, type);
+		 else
+			status = acpi_bus_get_device(chandle, &child);
+
+		 if (ACPI_FAILURE(status))
+			 continue;
+
+		if (ops->acpi_op_start) {
+			status = acpi_start_single_object(child);
+			if (ACPI_FAILURE(status))
+				continue;
+		}
 
 		/*
 		 * If the device is present, enabled, and functioning then
@@ -1257,8 +1278,50 @@ int acpi_bus_scan (struct acpi_device	*start)
 
 	return_VALUE(0);
 }
-EXPORT_SYMBOL(acpi_bus_scan);
 
+int
+acpi_bus_add (
+	struct acpi_device	**child,
+	struct acpi_device	*parent,
+	acpi_handle		handle,
+	int			type)
+{
+	int result;
+	struct acpi_bus_ops ops;
+
+	ACPI_FUNCTION_TRACE("acpi_bus_add");
+
+	result = acpi_add_single_object(child, parent, handle, type);
+	if (!result) {
+		memset(&ops, 0, sizeof(ops));
+		ops.acpi_op_add = 1;
+		result = acpi_bus_scan(*child, &ops);
+	}
+	return_VALUE(result);
+}
+EXPORT_SYMBOL(acpi_bus_add);
+
+int
+acpi_bus_start (
+	struct acpi_device *device)
+{
+	int result;
+	struct acpi_bus_ops ops;
+
+	ACPI_FUNCTION_TRACE("acpi_bus_start");
+
+	if (!device)
+		return_VALUE(-EINVAL);
+
+	result = acpi_start_single_object(device);
+	if (!result) {
+		memset(&ops, 0, sizeof(ops));
+		ops.acpi_op_start = 1;
+		result = acpi_bus_scan(device, &ops);
+	}
+	return_VALUE(result);
+}
+EXPORT_SYMBOL(acpi_bus_start);
 
 static int
 acpi_bus_trim(struct acpi_device	*start,
@@ -1331,13 +1394,19 @@ acpi_bus_scan_fixed (
 	/*
 	 * Enumerate all fixed-feature devices.
 	 */
-	if (acpi_fadt.pwr_button == 0)
-		result = acpi_bus_add(&device, acpi_root, 
+	if (acpi_fadt.pwr_button == 0) {
+		result = acpi_add_single_object(&device, acpi_root,
 			NULL, ACPI_BUS_TYPE_POWER_BUTTON);
+		if (!result)
+			result = acpi_start_single_object(device);
+	}
 
-	if (acpi_fadt.sleep_button == 0)
-		result = acpi_bus_add(&device, acpi_root, 
+	if (acpi_fadt.sleep_button == 0) {
+		result = acpi_add_single_object(&device, acpi_root,
 			NULL, ACPI_BUS_TYPE_SLEEP_BUTTON);
+		if (!result)
+			result = acpi_start_single_object(device);
+	}
 
 	return_VALUE(result);
 }
@@ -1346,6 +1415,7 @@ acpi_bus_scan_fixed (
 static int __init acpi_scan_init(void)
 {
 	int result;
+	struct acpi_bus_ops ops;
 
 	ACPI_FUNCTION_TRACE("acpi_scan_init");
 
@@ -1357,17 +1427,23 @@ static int __init acpi_scan_init(void)
 	/*
 	 * Create the root device in the bus's device tree
 	 */
-	result = acpi_bus_add(&acpi_root, NULL, ACPI_ROOT_OBJECT, 
+	result = acpi_add_single_object(&acpi_root, NULL, ACPI_ROOT_OBJECT,
 		ACPI_BUS_TYPE_SYSTEM);
 	if (result)
 		goto Done;
 
+	result = acpi_start_single_object(acpi_root);
+
 	/*
 	 * Enumerate devices in the ACPI namespace.
 	 */
 	result = acpi_bus_scan_fixed(acpi_root);
-	if (!result) 
-		result = acpi_bus_scan(acpi_root);
+	if (!result) {
+		memset(&ops, 0, sizeof(ops));
+		ops.acpi_op_add = 1;
+		ops.acpi_op_start = 1;
+		result = acpi_bus_scan(acpi_root, &ops);
+	}
 
 	if (result)
 		acpi_device_unregister(acpi_root, ACPI_BUS_REMOVAL_NORMAL);

drivers/char/moxa.c

@@ -451,7 +451,7 @@ static int __init moxa_init(void)
 		int n = (sizeof(moxa_pcibrds) / sizeof(moxa_pcibrds[0])) - 1;
 		i = 0;
 		while (i < n) {
-			while ((p = pci_find_device(moxa_pcibrds[i].vendor, moxa_pcibrds[i].device, p))!=NULL)
+			while ((p = pci_get_device(moxa_pcibrds[i].vendor, moxa_pcibrds[i].device, p))!=NULL)
 			{
 				if (pci_enable_device(p))
 					continue;