PCI: add proper MCFG support to let AMD boxes support MMCONFIG

@@ -158,9 +158,15 @@
 #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;

@@ -171,18 +177,38 @@
 		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

@@ -923,7 +949,6 @@
 	acpi_process_madt();
 
 	acpi_table_parse(ACPI_HPET, acpi_parse_hpet);
-	acpi_table_parse(ACPI_MCFG, acpi_parse_mcfg);
 
 	return 0;
 }

@@ -342,11 +342,19 @@
 
 /* PCI MMCONFIG */
 
+/* Defined in PCI Firmware Specification 3.0 */
+struct acpi_table_mcfg_config {
+	u32				base_address;
+	u32				base_reserved;
+	u16				pci_segment_group_number;
+	u8				start_bus_number;
+	u8				end_bus_number;
+	u8				reserved[4];
+} __attribute__ ((packed));
 struct acpi_table_mcfg {
 	struct acpi_table_header	header;
 	u8				reserved[8];
-	u32				base_address;
-	u32				base_reserved;
+	struct acpi_table_mcfg_config	config[0];
 } __attribute__ ((packed));
 
 /* Table Handlers */

@@ -391,6 +399,7 @@
 int acpi_get_table_header_early (enum acpi_table_id id, struct acpi_table_header **header);
 int acpi_table_parse_madt (enum acpi_madt_entry_id id, acpi_madt_entry_handler handler, unsigned int max_entries);
 int acpi_table_parse_srat (enum acpi_srat_entry_id id, acpi_madt_entry_handler handler, unsigned int max_entries);
+int acpi_parse_mcfg (unsigned long phys_addr, unsigned long size);
 void acpi_table_print (struct acpi_table_header *header, unsigned long phys_addr);
 void acpi_table_print_madt_entry (acpi_table_entry_header *madt);
 void acpi_table_print_srat_entry (acpi_table_entry_header *srat);

@@ -412,7 +421,8 @@
 
 extern int acpi_mp_config;
 
-extern u32 pci_mmcfg_base_addr;
+extern struct acpi_table_mcfg_config *pci_mmcfg_config;
+extern int pci_mmcfg_config_num;
 
 extern int sbf_port ;
 

@@ -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 */

@@ -27,7 +25,7 @@
 
 static inline void pci_exp_set_dev_base(int bus, int devfn)
 {
-	u32 dev_base = pci_mmcfg_base_addr | (bus << 20) | (devfn << 12);
+	u32 dev_base = pci_mmcfg_config[0].base_address | (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);

@@ -101,7 +99,11 @@
 {
 	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

@@ -7,15 +7,13 @@
 
 #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;
+static char *pci_mmcfg_virt;
 
 static inline char *pci_dev_base(unsigned int bus, unsigned int devfn)
 {

@@ -77,7 +75,11 @@
 {
 	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 +90,13 @@
 		return 0; 
 
 	/* RED-PEN i386 doesn't do _nocache right now */
-	pci_mmcfg_virt = ioremap_nocache(pci_mmcfg_base_addr, MMCONFIG_APER_SIZE);
+	pci_mmcfg_virt = ioremap_nocache(pci_mmcfg_config[0].base_address, MMCONFIG_APER_SIZE);
 	if (!pci_mmcfg_virt) { 
 		printk("PCI: Cannot map mmconfig aperture\n");
 		return 0;
 	}	
 
-	printk(KERN_INFO "PCI: Using MMCONFIG at %x\n", pci_mmcfg_base_addr);
+	printk(KERN_INFO "PCI: Using MMCONFIG at %x\n", pci_mmcfg_config[0].base_address);
 	raw_pci_ops = &pci_mmcfg;
 	pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;
 

@@ -22,10 +22,31 @@
 /*
  * Functions for accessing PCI configuration space with MMCONFIG accesses
  */
+static u32 get_base_addr(unsigned int seg, int bus)
+{
+	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(int bus, int devfn)
+static inline void pci_exp_set_dev_base(unsigned int seg, int bus, int devfn)
 {
-	u32 dev_base = pci_mmcfg_config[0].base_address | (bus << 20) | (devfn << 12);
+	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);

@@ -42,7 +63,7 @@
 
 	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:

@@ -71,7 +92,7 @@
 
 	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:

@@ -13,17 +13,44 @@
 #define MMCONFIG_APER_SIZE (256*1024*1024)
 
 /* Static virtual mapping of the MMCONFIG aperture */
-static char *pci_mmcfg_virt;
+struct mmcfg_virt {
+	struct acpi_table_mcfg_config *cfg;
+	char *virt;
+};
+static struct mmcfg_virt *pci_mmcfg_virt;
+
+static char *get_virt(unsigned int seg, int bus)
+{
+	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 bus, unsigned int devfn)
+static inline char *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn)
 {
-	return pci_mmcfg_virt + ((bus << 20) | (devfn << 12));
+
+	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;

@@ -46,7 +73,7 @@
 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;

@@ -73,6 +100,8 @@
 
 static int __init pci_mmcfg_init(void)
 {
+	int i;
+
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
 		return 0;
 

@@ -90,13 +119,22 @@
 		return 0; 
 
 	/* RED-PEN i386 doesn't do _nocache right now */
-	pci_mmcfg_virt = ioremap_nocache(pci_mmcfg_config[0].base_address, 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_config[0].base_address);
 	raw_pci_ops = &pci_mmcfg;
 	pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;
 

@@ -127,13 +127,6 @@
 	    (pci_mmcfg_config[0].base_address == 0))
 		goto out;
 
-	/* Kludge for now. Don't use mmconfig on AMD systems because
-	   those have some busses where mmconfig doesn't work,
-	   and we don't parse ACPI MCFG well enough to handle that. 
-	   Remove when proper handling is added. */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
-		goto out; 
-
 	printk(KERN_INFO "PCI: Using MMCONFIG\n");
 	raw_pci_ops = &pci_mmcfg;
 	pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;

@@ -111,13 +111,6 @@
 	    (pci_mmcfg_config[0].base_address == 0))
 		return 0;
 
-	/* Kludge for now. Don't use mmconfig on AMD systems because
-	   those have some busses where mmconfig doesn't work,
-	   and we don't parse ACPI MCFG well enough to handle that. 
-	   Remove when proper handling is added. */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
-		return 0; 
-
 	/* RED-PEN i386 doesn't do _nocache right now */
 	pci_mmcfg_virt = kmalloc(sizeof(*pci_mmcfg_virt) * pci_mmcfg_config_num, GFP_KERNEL);
 	if (pci_mmcfg_virt == NULL) {