"big box" x86 changes

88 lines not on this page · raw message

451 lines not on this page · raw message

index cbd42e5..645ee5e 100644
@@ -84,14 +84,41 @@ void __init reserve_early(unsigned long start, unsigned long end, char *name)
 		strncpy(r->name, name, sizeof(r->name) - 1);
 }
 
-void __init early_res_to_bootmem(void)
+void __init free_early(unsigned long start, unsigned long end)
+{
+	struct early_res *r;
+	int i, j;
+
+	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
+		r = &early_res[i];
+		if (start == r->start && end == r->end)
+			break;
+	}
+	if (i >= MAX_EARLY_RES || !early_res[i].end)
+		panic("free_early on not reserved area: %lx-%lx!", start, end);
+
+	for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
+		;
+
+	memcpy(&early_res[i], &early_res[i + 1],
+	       (j - 1 - i) * sizeof(struct early_res));
+
+	early_res[j - 1].end = 0;
+}
+
+void __init early_res_to_bootmem(unsigned long start, unsigned long end)
 {
 	int i;
+	unsigned long final_start, final_end;
 	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
 		struct early_res *r = &early_res[i];
-		printk(KERN_INFO "early res: %d [%lx-%lx] %s\n", i,
-			r->start, r->end - 1, r->name);
-		reserve_bootmem_generic(r->start, r->end - r->start);
+		final_start = max(start, r->start);
+		final_end = min(end, r->end);
+		if (final_start >= final_end)
+			continue;
+		printk(KERN_INFO "  early res: %d [%lx-%lx] %s\n", i,
+			final_start, final_end - 1, r->name);
+		reserve_bootmem_generic(final_start, final_end - final_start);
 	}
 }
 

index d31d6b7..e25c57b 100644
@@ -11,6 +11,7 @@
 #include <linux/string.h>
 #include <linux/percpu.h>
 #include <linux/start_kernel.h>
+#include <linux/io.h>
 
 #include <asm/processor.h>
 #include <asm/proto.h>

@@ -100,6 +101,24 @@ static void __init reserve_ebda_region(void)
 	reserve_early(lowmem, 0x100000, "BIOS reserved");
 }
 
+static void __init reserve_setup_data(void)
+{
+	struct setup_data *data;
+	unsigned long pa_data;
+	char buf[32];
+
+	if (boot_params.hdr.version < 0x0209)
+		return;
+	pa_data = boot_params.hdr.setup_data;
+	while (pa_data) {
+		data = early_ioremap(pa_data, sizeof(*data));
+		sprintf(buf, "setup data %x", data->type);
+		reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf);
+		pa_data = data->next;
+		early_iounmap(data, sizeof(*data));
+	}
+}
+
 void __init x86_64_start_kernel(char * real_mode_data)
 {
 	int i;

@@ -156,6 +175,7 @@ void __init x86_64_start_kernel(char * real_mode_data)
 #endif
 
 	reserve_ebda_region();
+	reserve_setup_data();
 
 	/*
 	 * At this point everything still needed from the boot loader

193 lines not on this page · raw message

243 lines not on this page · raw message

index 388b113..50a18e4 100644
@@ -77,10 +77,14 @@ void __init dma32_reserve_bootmem(void)
 	if (end_pfn <= MAX_DMA32_PFN)
 		return;
 
+	/*
+	 * check aperture_64.c allocate_aperture() for reason about
+	 * using 512M as goal
+	 */
 	align = 64ULL<<20;
 	size = round_up(dma32_bootmem_size, align);
 	dma32_bootmem_ptr = __alloc_bootmem_nopanic(size, align,
-				 __pa(MAX_DMA_ADDRESS));
+				 512ULL<<20);
 	if (dma32_bootmem_ptr)
 		dma32_bootmem_size = size;
 	else

@@ -88,7 +92,6 @@ void __init dma32_reserve_bootmem(void)
 }
 static void __init dma32_free_bootmem(void)
 {
-	int node;
 
 	if (end_pfn <= MAX_DMA32_PFN)
 		return;

@@ -96,9 +99,7 @@ static void __init dma32_free_bootmem(void)
 	if (!dma32_bootmem_ptr)
 		return;
 
-	for_each_online_node(node)
-		free_bootmem_node(NODE_DATA(node), __pa(dma32_bootmem_ptr),
-				  dma32_bootmem_size);
+	free_bootmem(__pa(dma32_bootmem_ptr), dma32_bootmem_size);
 
 	dma32_bootmem_ptr = NULL;
 	dma32_bootmem_size = 0;

95 lines not on this page · raw message

index 0cca626..e900757 100644
@@ -810,7 +810,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 {
 #ifdef CONFIG_NUMA
-	int nid = phys_to_nid(phys);
+	int nid, next_nid;
 #endif
 	unsigned long pfn = phys >> PAGE_SHIFT;
 

@@ -829,10 +829,14 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 
 	/* Should check here against the e820 map to avoid double free */
 #ifdef CONFIG_NUMA
+	nid = phys_to_nid(phys);
+	next_nid = phys_to_nid(phys + len - 1);
+	if (nid == next_nid)
 	reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
-#else
-	reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
+	else
 #endif
+	reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
+
 	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
 		dma_reserve += len / PAGE_SIZE;
 		set_dma_reserve(dma_reserve);

@@ -926,6 +930,10 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 /*
  * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
  */
+static long __meminitdata addr_start, addr_end;
+static void __meminitdata *p_start, *p_end;
+static int __meminitdata node_start;
+
 int __meminit
 vmemmap_populate(struct page *start_page, unsigned long size, int node)
 {

@@ -960,12 +968,32 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 							PAGE_KERNEL_LARGE);
 			set_pmd(pmd, __pmd(pte_val(entry)));
 
-			printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n",
-				addr, addr + PMD_SIZE - 1, p, node);
+			/* check to see if we have contiguous blocks */
+			if (p_end != p || node_start != node) {
+				if (p_start)
+					printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+						addr_start, addr_end-1, p_start, p_end-1, node_start);
+				addr_start = addr;
+				node_start = node;
+				p_start = p;
+			}
+			addr_end = addr + PMD_SIZE;
+			p_end = p + PMD_SIZE;
 		} else {
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
 		}
 	}
 	return 0;
 }
+
+void __meminit vmemmap_populate_print_last(void)
+{
+	if (p_start) {
+		printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+			addr_start, addr_end-1, p_start, p_end-1, node_start);
+		p_start = NULL;
+		p_end = NULL;
+		node_start = 0;
+	}
+}
 #endif

index 86808e6..1f476e4 100644
@@ -13,12 +13,15 @@
 #include <linux/nodemask.h>
 #include <asm/io.h>
 #include <linux/pci_ids.h>
+#include <linux/acpi.h>
 #include <asm/types.h>
 #include <asm/mmzone.h>
 #include <asm/proto.h>
 #include <asm/e820.h>
 #include <asm/pci-direct.h>
 #include <asm/numa.h>
+#include <asm/mpspec.h>
+#include <asm/apic.h>
 
 static __init int find_northbridge(void)
 {

@@ -44,6 +47,30 @@ static __init int find_northbridge(void)
 	return -1;
 }
 
+static __init void early_get_boot_cpu_id(void)
+{
+	/*
+	 * need to get boot_cpu_id so can use that to create apicid_to_node
+	 * in k8_scan_nodes()
+	 */
+	/*
+	 * Find possible boot-time SMP configuration:
+	 */
+	early_find_smp_config();
+#ifdef CONFIG_ACPI
+	/*
+	 * Read APIC information from ACPI tables.
+	 */
+	early_acpi_boot_init();
+#endif
+	/*
+	 * get boot-time SMP configuration:
+	 */
+	if (smp_found_config)
+		early_get_smp_config();
+	early_init_lapic_mapping();
+}
+
 int __init k8_scan_nodes(unsigned long start, unsigned long end)
 {
 	unsigned long prevbase;

@@ -56,6 +83,7 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
 	unsigned cores;
 	unsigned bits;
 	int j;
+	unsigned apicid_base;
 
 	if (!early_pci_allowed())
 		return -1;

@@ -174,11 +202,19 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
 	/* use the coreid bits from early_identify_cpu */
 	bits = boot_cpu_data.x86_coreid_bits;
 	cores = (1<<bits);
+	apicid_base = 0;
+	/* need to get boot_cpu_id early for system with apicid lifting */
+	early_get_boot_cpu_id();
+	if (boot_cpu_physical_apicid > 0) {
+		printk(KERN_INFO "BSP APIC ID: %02x\n",
+				 boot_cpu_physical_apicid);
+		apicid_base = boot_cpu_physical_apicid;
+	}
 
 	for (i = 0; i < 8; i++) {
 		if (nodes[i].start != nodes[i].end) {
 			nodeid = nodeids[i];
-			for (j = 0; j < cores; j++)
+			for (j = apicid_base; j < cores + apicid_base; j++)
 				apicid_to_node[(nodeid << bits) + j] = i;
 			setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 		}

62 lines not on this page · raw message

117 lines not on this page · raw message

127 lines not on this page · raw message

index 42f3e4c..21d1e0e 100644
@@ -258,7 +258,8 @@ void __init pci_direct_init(int type)
 {
 	if (type == 0)
 		return;
-	printk(KERN_INFO "PCI: Using configuration type %d\n", type);
+	printk(KERN_INFO "PCI: Using configuration type %d for base access\n",
+		 type);
 	if (type == 1)
 		raw_pci_ops = &pci_direct_conf1;
 	else

@@ -275,8 +276,10 @@ int __init pci_direct_probe(void)
 	if (!region)
 		goto type2;
 
-	if (pci_check_type1())
+	if (pci_check_type1()) {
+		raw_pci_ops = &pci_direct_conf1;
 		return 1;
+	}
 	release_resource(region);
 
  type2:

@@ -290,7 +293,6 @@ int __init pci_direct_probe(void)
 		goto fail2;
 
 	if (pci_check_type2()) {
-		printk(KERN_INFO "PCI: Using configuration type 2\n");
 		raw_pci_ops = &pci_direct_conf2;
 		return 2;
 	}

index a5ef5f5..b60b2ab 100644
@@ -493,3 +493,20 @@ static void __devinit pci_siemens_interrupt_controller(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SIEMENS, 0x0015,
 			  pci_siemens_interrupt_controller);
+
+/*
+ * Regular PCI devices have 256 bytes, but AMD Family 10h Opteron ext config
+ * have 4096 bytes.  Even if the device is capable, that doesn't mean we can
+ * access it.  Maybe we don't have a way to generate extended config space
+ * accesses.   So check it
+ */
+static void fam10h_pci_cfg_space_size(struct pci_dev *dev)
+{
+	dev->cfg_size = pci_cfg_space_size_ext(dev, 0);
+}
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, fam10h_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, fam10h_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, fam10h_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, fam10h_pci_cfg_space_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, fam10h_pci_cfg_space_size);

index 3de9f9b..f098a6e 100644
@@ -6,16 +6,13 @@
    in the right sequence from here. */
 static __init int pci_access_init(void)
 {
-	int type __maybe_unused = 0;
-
 #ifdef CONFIG_PCI_DIRECT
+	int type = 0;
+
 	type = pci_direct_probe();
 #endif
-#ifdef CONFIG_PCI_MMCONFIG
-	pci_mmcfg_init(type);
-#endif
-	if (raw_pci_ops)
-		return 0;
+	pci_mmcfg_early_init();
+
 #ifdef CONFIG_PCI_BIOS
 	pci_pcbios_init();
 #endif

@@ -28,10 +25,14 @@ static __init int pci_access_init(void)
 #ifdef CONFIG_PCI_DIRECT
 	pci_direct_init(type);
 #endif
-	if (!raw_pci_ops)
+	if (!raw_pci_ops && !raw_pci_ext_ops)
 		printk(KERN_ERR
 		"PCI: Fatal: No config space access function found\n");
 
+	dmi_check_pciprobe();
+
+	dmi_check_skip_isa_align();
+
 	return 0;
 }
 arch_initcall(pci_access_init);

index 579745c..0908fca 100644
@@ -136,9 +136,11 @@ static void __init pirq_peer_trick(void)
 		busmap[e->bus] = 1;
 	}
 	for(i = 1; i < 256; i++) {
+		int node;
 		if (!busmap[i] || pci_find_bus(0, i))
 			continue;
-		if (pci_scan_bus_with_sysdata(i))
+		node = get_mp_bus_to_node(i);
+		if (pci_scan_bus_on_node(i, &pci_root_ops, node))
 			printk(KERN_INFO "PCI: Discovered primary peer "
 			       "bus %02x [IRQ]\n", i);
 	}

602 lines not on this page · raw message

index e041ced..a67921c 100644
@@ -12,6 +12,7 @@
 static void __devinit pcibios_fixup_peer_bridges(void)
 {
 	int n, devfn;
+	long node;
 
 	if (pcibios_last_bus <= 0 || pcibios_last_bus >= 0xff)
 		return;

@@ -21,12 +22,13 @@ static void __devinit pcibios_fixup_peer_bridges(void)
 		u32 l;
 		if (pci_find_bus(0, n))
 			continue;
+		node = get_mp_bus_to_node(n);
 		for (devfn = 0; devfn < 256; devfn += 8) {
 			if (!raw_pci_read(0, n, devfn, PCI_VENDOR_ID, 2, &l) &&
 			    l != 0x0000 && l != 0xffff) {
 				DBG("Found device at %02x:%02x [%04x]\n", n, devfn, l);
 				printk(KERN_INFO "PCI: Discovered peer bus %02x\n", n);
-				pci_scan_bus_with_sysdata(n);
+				pci_scan_bus_on_node(n, &pci_root_ops, node);
 				break;
 			}
 		}

330 lines not on this page · raw message

index 081816a..f3c761d 100644
@@ -136,3 +136,7 @@ int __init pci_mmcfg_arch_init(void)
 	raw_pci_ext_ops = &pci_mmcfg;
 	return 1;
 }
+
+void __init pci_mmcfg_arch_free(void)
+{
+}

index 9207fd4..a199416 100644
@@ -127,7 +127,7 @@ static void __iomem * __init mcfg_ioremap(struct acpi_mcfg_allocation *cfg)
 int __init pci_mmcfg_arch_init(void)
 {
 	int i;
-	pci_mmcfg_virt = kmalloc(sizeof(*pci_mmcfg_virt) *
+	pci_mmcfg_virt = kzalloc(sizeof(*pci_mmcfg_virt) *
 				 pci_mmcfg_config_num, GFP_KERNEL);
 	if (pci_mmcfg_virt == NULL) {
 		printk(KERN_ERR "PCI: Can not allocate memory for mmconfig structures\n");

@@ -141,9 +141,29 @@ int __init pci_mmcfg_arch_init(void)
 			printk(KERN_ERR "PCI: Cannot map mmconfig aperture for "
 					"segment %d\n",
 				pci_mmcfg_config[i].pci_segment);
+			pci_mmcfg_arch_free();
 			return 0;
 		}
 	}
 	raw_pci_ext_ops = &pci_mmcfg;
 	return 1;
 }
+
+void __init pci_mmcfg_arch_free(void)
+{
+	int i;
+
+	if (pci_mmcfg_virt == NULL)
+		return;
+
+	for (i = 0; i < pci_mmcfg_config_num; ++i) {
+		if (pci_mmcfg_virt[i].virt) {
+			iounmap(pci_mmcfg_virt[i].virt);
+			pci_mmcfg_virt[i].virt = NULL;
+			pci_mmcfg_virt[i].cfg = NULL;
+		}
+	}
+
+	kfree(pci_mmcfg_virt);
+	pci_mmcfg_virt = NULL;
+}

new file mode 100644
index 0000000..0229439
@@ -0,0 +1,23 @@
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/topology.h>
+
+#define BUS_NR 256
+
+static unsigned char mp_bus_to_node[BUS_NR];
+
+void set_mp_bus_to_node(int busnum, int node)
+{
+	if (busnum >= 0 &&  busnum < BUS_NR)
+	mp_bus_to_node[busnum] = (unsigned char) node;
+}
+
+int get_mp_bus_to_node(int busnum)
+{
+	int node;
+
+	if (busnum < 0 || busnum > (BUS_NR - 1))
+		return 0;
+	node = mp_bus_to_node[busnum];
+	return node;
+}

index c4bddae..3b0db9b 100644
@@ -26,6 +26,7 @@
 #define PCI_ASSIGN_ALL_BUSSES	0x4000
 #define PCI_CAN_SKIP_ISA_ALIGN	0x8000
 #define PCI_USE__CRS		0x10000
+#define PCI_CHECK_ENABLE_AMD_MMCONF	0x20000
 
 extern unsigned int pci_probe;
 extern unsigned long pirq_table_addr;

@@ -37,6 +38,9 @@ enum pci_bf_sort_state {
 	pci_dmi_bf,
 };
 
+extern void __init dmi_check_pciprobe(void);
+extern void __init dmi_check_skip_isa_align(void);
+
 /* pci-i386.c */
 
 extern unsigned int pcibios_max_latency;

@@ -97,11 +101,11 @@ extern struct pci_raw_ops pci_direct_conf1;
 extern int pci_direct_probe(void);
 extern void pci_direct_init(int type);
 extern void pci_pcbios_init(void);
-extern void pci_mmcfg_init(int type);
 
 /* pci-mmconfig.c */
 
 extern int __init pci_mmcfg_arch_init(void);
+extern void __init pci_mmcfg_arch_free(void);
 
 /*
  * AMD Fam10h CPUs are buggy, and cannot access MMIO config space

index 2d1955c..a6dbcf4 100644
@@ -35,6 +35,7 @@
 #ifdef CONFIG_X86
 #include <asm/mpspec.h>
 #endif
+#include <linux/pci.h>
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
 

@@ -784,6 +785,7 @@ static int __init acpi_init(void)
 	result = acpi_bus_init();
 
 	if (!result) {
+		pci_mmcfg_late_init();
 		if (!(pm_flags & PM_APM))
 			pm_flags |= PM_ACPI;
 		else {

index 9248e09..be288b5 100644
@@ -787,6 +787,10 @@ int device_add(struct device *dev)
 	parent = get_device(dev->parent);
 	setup_parent(dev, parent);
 
+	/* use parent numa_node */
+	if (parent)
+		set_dev_node(dev, dev_to_node(parent));
+
 	/* first, register with generic layer. */
 	error = kobject_add(&dev->kobj, dev->kobj.parent, "%s", dev->bus_id);
 	if (error)

@@ -1306,8 +1310,11 @@ int device_move(struct device *dev, struct device *new_parent)
 	dev->parent = new_parent;
 	if (old_parent)
 		klist_remove(&dev->knode_parent);
-	if (new_parent)
+	if (new_parent) {
 		klist_add_tail(&dev->knode_parent, &new_parent->klist_children);
+		set_dev_node(dev, dev_to_node(new_parent));
+	}
+
 	if (!dev->class)
 		goto out_put;
 	error = device_move_class_links(dev, old_parent, new_parent);

@@ -1317,9 +1324,12 @@ int device_move(struct device *dev, struct device *new_parent)
 		if (!kobject_move(&dev->kobj, &old_parent->kobj)) {
 			if (new_parent)
 				klist_remove(&dev->knode_parent);
-			if (old_parent)
+			dev->parent = old_parent;
+			if (old_parent) {
 				klist_add_tail(&dev->knode_parent,
 					       &old_parent->klist_children);
+				set_dev_node(dev, dev_to_node(old_parent));
+			}
 		}
 		cleanup_glue_dir(dev, new_parent_kobj);
 		put_device(new_parent);

index d8200ac..e77b321 100644
@@ -264,11 +264,7 @@ static int __devinit aperture_valid(u64 aper, u32 size)
 		printk(KERN_ERR PFX "No aperture\n");
 		return 0;
 	}
-	if (size < 32*1024*1024) {
-		printk(KERN_ERR PFX "Aperture too small (%d MB)\n", size>>20);
-		return 0;
-	}
-       if ((u64)aper + size > 0x100000000ULL) {
+	if ((u64)aper + size > 0x100000000ULL) {
 		printk(KERN_ERR PFX "Aperture out of bounds\n");
 		return 0;
 	}

@@ -276,6 +272,10 @@ static int __devinit aperture_valid(u64 aper, u32 size)
 		printk(KERN_ERR PFX "Aperture pointing to RAM\n");
 		return 0;
 	}
+	if (size < 32*1024*1024) {
+		printk(KERN_ERR PFX "Aperture too small (%d MB)\n", size>>20);
+		return 0;
+	}
 
 	/* Request the Aperture. This catches cases when someone else
 	   already put a mapping in there - happens with some very broken BIOS

@@ -331,6 +331,17 @@ static __devinit int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp,
 	pci_read_config_dword(agp, 0x10, &aper_low);
 	pci_read_config_dword(agp, 0x14, &aper_hi);
 	aper = (aper_low & ~((1<<22)-1)) | ((u64)aper_hi << 32);
+
+	/*
+	 * On some sick chips APSIZE is 0. This means it wants 4G
+	 * so let double check that order, and lets trust the AMD NB settings
+	 */
+	if (order >=0 && aper + (32ULL<<(20 + order)) > 0x100000000ULL) {
+		printk(KERN_INFO "Aperture size %u MB is not right, using settings from NB\n",
+				  32 << order);
+		order = nb_order;
+	}
+
 	printk(KERN_INFO PFX "Aperture from AGP @ %Lx size %u MB\n", aper, 32 << order);
 	if (order < 0 || !aperture_valid(aper, (32*1024*1024)<<order))
 		return -1;

index f991359..4a55bf3 100644
@@ -842,11 +842,14 @@ static void set_pcie_port_type(struct pci_dev *pdev)
  * reading the dword at 0x100 which must either be 0 or a valid extended
  * capability header.
  */
-int pci_cfg_space_size(struct pci_dev *dev)
+int pci_cfg_space_size_ext(struct pci_dev *dev, unsigned check_exp_pcix)
 {
 	int pos;
 	u32 status;
 
+	if (!check_exp_pcix)
+		goto skip;
+
 	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
 	if (!pos) {
 		pos = pci_find_capability(dev, PCI_CAP_ID_PCIX);

@@ -858,6 +861,7 @@ int pci_cfg_space_size(struct pci_dev *dev)
 			goto fail;
 	}
 
+ skip:
 	if (pci_read_config_dword(dev, 256, &status) != PCIBIOS_SUCCESSFUL)
 		goto fail;
 	if (status == 0xffffffff)

@@ -869,6 +873,11 @@ int pci_cfg_space_size(struct pci_dev *dev)
 	return PCI_CFG_SPACE_SIZE;
 }
 
+int pci_cfg_space_size(struct pci_dev *dev)
+{
+	return pci_cfg_space_size_ext(dev, 1);
+}
+
 static void pci_release_bus_bridge_dev(struct device *dev)
 {
 	kfree(dev);

@@ -964,7 +973,6 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus)
 	dev->dev.release = pci_release_dev;
 	pci_dev_get(dev);
 
-	set_dev_node(&dev->dev, pcibus_to_node(bus));
 	dev->dev.dma_mask = &dev->dma_mask;
 	dev->dev.dma_parms = &dev->dma_parms;
 	dev->dev.coherent_dma_mask = 0xffffffffull;

@@ -1080,6 +1088,10 @@ unsigned int __devinit pci_scan_child_bus(struct pci_bus *bus)
 	return max;
 }
 
+void __attribute__((weak)) set_pci_bus_resources_arch_default(struct pci_bus *b)
+{
+}
+
 struct pci_bus * pci_create_bus(struct device *parent,
 		int bus, struct pci_ops *ops, void *sysdata)
 {

@@ -1119,6 +1131,9 @@ struct pci_bus * pci_create_bus(struct device *parent,
 		goto dev_reg_err;
[… more lines in the raw message]

Lines of this file are not shown. View the raw message.

index 5115135..e865990 100644

Lines of this file are not shown. View the raw message.

index f478c57..71c4d68 100644

Lines of this file are not shown. View the raw message.

index ddd8e24..30bbde0 100644

Lines of this file are not shown. View the raw message.

index 2207326..0e6d6b0 100644

Lines of this file are not shown. View the raw message.

index 2c7e003..41f7ce7 100644

Lines of this file are not shown. View the raw message.

index f20410d..13779aa 100644

Lines of this file are not shown. View the raw message.

index b695875..286d315 100644

Lines of this file are not shown. View the raw message.

index 2924913..abc998f 100644

Lines of this file are not shown. View the raw message.

157 lines not on this page · raw message

index 98d6b39..7e91913 100644

Lines of this file are not shown. View the raw message.

index 4fe605f..94448e6 100644

Lines of this file are not shown. View the raw message.

index cbd42e5..f95fdab 100644
@@ -84,14 +84,19 @@ void __init reserve_early(unsigned long start, unsigned long end, char *name)
 		strncpy(r->name, name, sizeof(r->name) - 1);
 }
 
-void __init early_res_to_bootmem(void)
+void __init early_res_to_bootmem(unsigned long start, unsigned long end)
 {
 	int i;
+	unsigned long final_start, final_end;
 	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
 		struct early_res *r = &early_res[i];
-		printk(KERN_INFO "early res: %d [%lx-%lx] %s\n", i,
-			r->start, r->end - 1, r->name);
-		reserve_bootmem_generic(r->start, r->end - r->start);
+		final_start = max(start, r->start);
+		final_end = min(end, r->end);
+		if (final_start >= final_end)
+			continue;
+		printk(KERN_INFO "  early res: %d [%lx-%lx] %s\n", i,
+			final_start, final_end - 1, r->name);
+		reserve_bootmem_generic(final_start, final_end - final_start);
 	}
 }
 

index 17bdf23..de9c870 100644
@@ -190,6 +190,7 @@ contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
 	bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
 	e820_register_active_regions(0, start_pfn, end_pfn);
 	free_bootmem_with_active_regions(0, end_pfn);
+	early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
 	reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
 }
 #endif

@@ -397,8 +398,6 @@ void __init setup_arch(char **cmdline_p)
 	contig_initmem_init(0, end_pfn);
 #endif
 
-	early_res_to_bootmem();
-
 	dma32_reserve_bootmem();
 
 #ifdef CONFIG_ACPI_SLEEP

index 0cca626..e900757 100644
@@ -810,7 +810,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 {
 #ifdef CONFIG_NUMA
-	int nid = phys_to_nid(phys);
+	int nid, next_nid;
 #endif
 	unsigned long pfn = phys >> PAGE_SHIFT;
 

@@ -829,10 +829,14 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 
 	/* Should check here against the e820 map to avoid double free */
 #ifdef CONFIG_NUMA
+	nid = phys_to_nid(phys);
+	next_nid = phys_to_nid(phys + len - 1);
+	if (nid == next_nid)
 	reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
-#else
-	reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
+	else
 #endif
+	reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
+
 	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
 		dma_reserve += len / PAGE_SIZE;
 		set_dma_reserve(dma_reserve);

@@ -926,6 +930,10 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 /*
  * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
  */
+static long __meminitdata addr_start, addr_end;
+static void __meminitdata *p_start, *p_end;
+static int __meminitdata node_start;
+
 int __meminit
 vmemmap_populate(struct page *start_page, unsigned long size, int node)
 {

@@ -960,12 +968,32 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 							PAGE_KERNEL_LARGE);
 			set_pmd(pmd, __pmd(pte_val(entry)));
 
-			printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n",
-				addr, addr + PMD_SIZE - 1, p, node);
+			/* check to see if we have contiguous blocks */
+			if (p_end != p || node_start != node) {
+				if (p_start)
+					printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+						addr_start, addr_end-1, p_start, p_end-1, node_start);
+				addr_start = addr;
+				node_start = node;
+				p_start = p;
+			}
+			addr_end = addr + PMD_SIZE;
+			p_end = p + PMD_SIZE;
 		} else {
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
 		}
 	}
 	return 0;
 }
+
+void __meminit vmemmap_populate_print_last(void)
+{
+	if (p_start) {
+		printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+			addr_start, addr_end-1, p_start, p_end-1, node_start);
+		p_start = NULL;
+		p_end = NULL;
+		node_start = 0;
+	}
+}
 #endif

62 lines not on this page · raw message

index f478c57..4c6ad98 100644
@@ -48,7 +48,7 @@ extern struct e820map e820;
 extern void update_e820(void);
 
 extern void reserve_early(unsigned long start, unsigned long end, char *name);
-extern void early_res_to_bootmem(void);
+extern void early_res_to_bootmem(unsigned long start, unsigned long end);
 
 #endif/*!__ASSEMBLY__*/
 

index b695875..286d315 100644
@@ -1229,6 +1229,7 @@ void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
 int vmemmap_populate_basepages(struct page *start_page,
 						unsigned long pages, int node);
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
+void vmemmap_populate_print_last(void);
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */

276 lines not on this page · raw message

index 98d6b39..7e91913 100644
@@ -295,6 +295,9 @@ struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 	return NULL;
 }
 
+void __attribute__((weak)) __meminit vmemmap_populate_print_last(void)
+{
+}
 /*
  * Allocate the accumulated non-linear sections, allocate a mem_map
  * for each and record the physical to section mapping.

@@ -304,22 +307,50 @@ void __init sparse_init(void)
 	unsigned long pnum;
 	struct page *map;
 	unsigned long *usemap;
+	unsigned long **usemap_map;
+	int size;
+
+	/*
+	 * map is using big page (aka 2M in x86 64 bit)
+	 * usemap is less one page (aka 24 bytes)
+	 * so alloc 2M (with 2M align) and 24 bytes in turn will
+	 * make next 2M slip to one more 2M later.
+	 * then in big system, the memory will have a lot of holes...
+	 * here try to allocate 2M pages continously.
+	 *
+	 * powerpc need to call sparse_init_one_section right after each
+	 * sparse_early_mem_map_alloc, so allocate usemap_map at first.
+	 */
+	size = sizeof(unsigned long *) * NR_MEM_SECTIONS;
+	usemap_map = alloc_bootmem(size);
+	if (!usemap_map)
+		panic("can not allocate usemap_map\n");
 
 	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
 		if (!present_section_nr(pnum))
 			continue;
+		usemap_map[pnum] = sparse_early_usemap_alloc(pnum);
+	}
 
-		map = sparse_early_mem_map_alloc(pnum);
-		if (!map)
+	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+		if (!present_section_nr(pnum))
 			continue;
 
-		usemap = sparse_early_usemap_alloc(pnum);
+		usemap = usemap_map[pnum];
 		if (!usemap)
 			continue;
 
+		map = sparse_early_mem_map_alloc(pnum);
+		if (!map)
+			continue;
+
 		sparse_init_one_section(__nr_to_section(pnum), pnum, map,
 								usemap);
 	}
+
+	vmemmap_populate_print_last();
+
+	free_bootmem(__pa(usemap_map), size);
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG

Index: linux-x86.q/arch/x86/mm/init_64.c
===================================================================
@@ -810,7 +810,7 @@ void free_initrd_mem(unsigned long start
 void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 {
 #ifdef CONFIG_NUMA
-	int nid = phys_to_nid(phys);
+	int nid, next_nid;
 #endif
 	unsigned long pfn = phys >> PAGE_SHIFT;
 

@@ -829,10 +829,16 @@ void __init reserve_bootmem_generic(unsi
 
 	/* Should check here against the e820 map to avoid double free */
 #ifdef CONFIG_NUMA
-	reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+	nid = phys_to_nid(phys);
+	next_nid = phys_to_nid(phys + len - 1);
+	if (nid == next_nid)
+		reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+	else
+		reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
 #else
 	reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
 #endif
+
 	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
 		dma_reserve += len / PAGE_SIZE;
 		set_dma_reserve(dma_reserve);

Index: linux-x86.q/arch/x86/mm/init_64.c
===================================================================
@@ -810,10 +810,8 @@ void free_initrd_mem(unsigned long start
 
 void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 {
-#ifdef CONFIG_NUMA
-	int nid, next_nid;
-#endif
 	unsigned long pfn = phys >> PAGE_SHIFT;
+	int nid, next_nid;
 
 	if (pfn >= end_pfn) {
 		/*

@@ -829,16 +827,12 @@ void __init reserve_bootmem_generic(unsi
 	}
 
 	/* Should check here against the e820 map to avoid double free */
-#ifdef CONFIG_NUMA
 	nid = phys_to_nid(phys);
 	next_nid = phys_to_nid(phys + len - 1);
 	if (nid == next_nid)
 		reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
 	else
 		reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
-#else
-	reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
-#endif
 
 	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
 		dma_reserve += len / PAGE_SIZE;

index cbd42e5..f95fdab 100644
@@ -84,14 +84,19 @@ void __init reserve_early(unsigned long start, unsigned long end, char *name)
 		strncpy(r->name, name, sizeof(r->name) - 1);
 }
 
-void __init early_res_to_bootmem(void)
+void __init early_res_to_bootmem(unsigned long start, unsigned long end)
 {
 	int i;
+	unsigned long final_start, final_end;
 	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
 		struct early_res *r = &early_res[i];
-		printk(KERN_INFO "early res: %d [%lx-%lx] %s\n", i,
-			r->start, r->end - 1, r->name);
-		reserve_bootmem_generic(r->start, r->end - r->start);
+		final_start = max(start, r->start);
+		final_end = min(end, r->end);
+		if (final_start >= final_end)
+			continue;
+		printk(KERN_INFO "  early res: %d [%lx-%lx] %s\n", i,
+			final_start, final_end - 1, r->name);
+		reserve_bootmem_generic(final_start, final_end - final_start);
 	}
 }
 

index 17bdf23..de9c870 100644
@@ -190,6 +190,7 @@ contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
 	bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
 	e820_register_active_regions(0, start_pfn, end_pfn);
 	free_bootmem_with_active_regions(0, end_pfn);
+	early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
 	reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
 }
 #endif

@@ -397,8 +398,6 @@ void __init setup_arch(char **cmdline_p)
 	contig_initmem_init(0, end_pfn);
 #endif
 
-	early_res_to_bootmem();
-
 	dma32_reserve_bootmem();
 
 #ifdef CONFIG_ACPI_SLEEP

index 0cca626..5fbb865 100644
@@ -810,7 +810,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 {
 #ifdef CONFIG_NUMA
-	int nid = phys_to_nid(phys);
+	int nid, next_nid;
 #endif
 	unsigned long pfn = phys >> PAGE_SHIFT;
 

@@ -829,10 +829,16 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 
 	/* Should check here against the e820 map to avoid double free */
 #ifdef CONFIG_NUMA
-	reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+	nid = phys_to_nid(phys);
+	next_nid = phys_to_nid(phys + len - 1);
+	if (nid == next_nid)
+		reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+	else
+		reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
 #else
 	reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
 #endif
+
 	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
 		dma_reserve += len / PAGE_SIZE;
 		set_dma_reserve(dma_reserve);

@@ -926,6 +932,10 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 /*
  * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
  */
+static long __meminitdata addr_start, addr_end;
+static void __meminitdata *p_start, *p_end;
+static int __meminitdata node_start;
+
 int __meminit
 vmemmap_populate(struct page *start_page, unsigned long size, int node)
 {

@@ -960,12 +970,32 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 							PAGE_KERNEL_LARGE);
 			set_pmd(pmd, __pmd(pte_val(entry)));
 
-			printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n",
-				addr, addr + PMD_SIZE - 1, p, node);
+			/* check to see if we have contiguous blocks */
+			if (p_end != p || node_start != node) {
+				if (p_start)
+					printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+						addr_start, addr_end-1, p_start, p_end-1, node_start);
+				addr_start = addr;
+				node_start = node;
+				p_start = p;
+			}
+			addr_end = addr + PMD_SIZE;
+			p_end = p + PMD_SIZE;
 		} else {
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
 		}
 	}
 	return 0;
 }
+
+void __meminit vmemmap_populate_print_last(void)
+{
+	if (p_start) {
+		printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+			addr_start, addr_end-1, p_start, p_end-1, node_start);
+		p_start = NULL;
+		p_end = NULL;
+		node_start = 0;
+	}
+}
 #endif

61 lines not on this page · raw message

index f478c57..4c6ad98 100644
@@ -48,7 +48,7 @@ extern struct e820map e820;
 extern void update_e820(void);
 
 extern void reserve_early(unsigned long start, unsigned long end, char *name);
-extern void early_res_to_bootmem(void);
+extern void early_res_to_bootmem(unsigned long start, unsigned long end);
 
 #endif/*!__ASSEMBLY__*/
 

index b695875..286d315 100644
@@ -1229,6 +1229,7 @@ void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
 int vmemmap_populate_basepages(struct page *start_page,
 						unsigned long pages, int node);
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
+void vmemmap_populate_print_last(void);
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */

282 lines not on this page · raw message

index 98d6b39..7e91913 100644
@@ -295,6 +295,9 @@ struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 	return NULL;
 }
 
+void __attribute__((weak)) __meminit vmemmap_populate_print_last(void)
+{
+}
 /*
  * Allocate the accumulated non-linear sections, allocate a mem_map
  * for each and record the physical to section mapping.

@@ -304,22 +307,50 @@ void __init sparse_init(void)
 	unsigned long pnum;
 	struct page *map;
 	unsigned long *usemap;
+	unsigned long **usemap_map;
+	int size;
+
+	/*
+	 * map is using big page (aka 2M in x86 64 bit)
+	 * usemap is less one page (aka 24 bytes)
+	 * so alloc 2M (with 2M align) and 24 bytes in turn will
+	 * make next 2M slip to one more 2M later.
+	 * then in big system, the memory will have a lot of holes...
+	 * here try to allocate 2M pages continously.
+	 *
+	 * powerpc need to call sparse_init_one_section right after each
+	 * sparse_early_mem_map_alloc, so allocate usemap_map at first.
+	 */
+	size = sizeof(unsigned long *) * NR_MEM_SECTIONS;
+	usemap_map = alloc_bootmem(size);
+	if (!usemap_map)
+		panic("can not allocate usemap_map\n");
 
 	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
 		if (!present_section_nr(pnum))
 			continue;
+		usemap_map[pnum] = sparse_early_usemap_alloc(pnum);
+	}
 
-		map = sparse_early_mem_map_alloc(pnum);
-		if (!map)
+	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+		if (!present_section_nr(pnum))
 			continue;
 
-		usemap = sparse_early_usemap_alloc(pnum);
+		usemap = usemap_map[pnum];
 		if (!usemap)
 			continue;
 
+		map = sparse_early_mem_map_alloc(pnum);
+		if (!map)
+			continue;
+
 		sparse_init_one_section(__nr_to_section(pnum), pnum, map,
 								usemap);
 	}
+
+	vmemmap_populate_print_last();
+
+	free_bootmem(__pa(usemap_map), size);
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG

index 79f0d52..645ee5e 100644
@@ -106,14 +106,19 @@ void __init free_early(unsigned long start, unsigned long end)
 	early_res[j - 1].end = 0;
 }
 
-void __init early_res_to_bootmem(void)
+void __init early_res_to_bootmem(unsigned long start, unsigned long end)
 {
 	int i;
+	unsigned long final_start, final_end;
 	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
 		struct early_res *r = &early_res[i];
-		printk(KERN_INFO "early res: %d [%lx-%lx] %s\n", i,
-			r->start, r->end - 1, r->name);
-		reserve_bootmem_generic(r->start, r->end - r->start);
+		final_start = max(start, r->start);
+		final_end = min(end, r->end);
+		if (final_start >= final_end)
+			continue;
+		printk(KERN_INFO "  early res: %d [%lx-%lx] %s\n", i,
+			final_start, final_end - 1, r->name);
+		reserve_bootmem_generic(final_start, final_end - final_start);
 	}
 }
 

index b04e2c0..60e64c8 100644
@@ -190,6 +190,7 @@ contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
 	bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
 	e820_register_active_regions(0, start_pfn, end_pfn);
 	free_bootmem_with_active_regions(0, end_pfn);
+	early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
 	reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
 }
 #endif

@@ -421,8 +422,6 @@ void __init setup_arch(char **cmdline_p)
 	contig_initmem_init(0, end_pfn);
 #endif
 
-	early_res_to_bootmem();
-
 	dma32_reserve_bootmem();
 
 #ifdef CONFIG_ACPI_SLEEP

index 0cca626..5fbb865 100644
@@ -810,7 +810,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 {
 #ifdef CONFIG_NUMA
-	int nid = phys_to_nid(phys);
+	int nid, next_nid;
 #endif
 	unsigned long pfn = phys >> PAGE_SHIFT;
 

@@ -829,10 +829,16 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 
 	/* Should check here against the e820 map to avoid double free */
 #ifdef CONFIG_NUMA
-	reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+	nid = phys_to_nid(phys);
+	next_nid = phys_to_nid(phys + len - 1);
+	if (nid == next_nid)
+		reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+	else
+		reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
 #else
 	reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
 #endif
+
 	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
 		dma_reserve += len / PAGE_SIZE;
 		set_dma_reserve(dma_reserve);

@@ -926,6 +932,10 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 /*
  * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
  */
+static long __meminitdata addr_start, addr_end;
+static void __meminitdata *p_start, *p_end;
+static int __meminitdata node_start;
+
 int __meminit
 vmemmap_populate(struct page *start_page, unsigned long size, int node)
 {

@@ -960,12 +970,32 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 							PAGE_KERNEL_LARGE);
 			set_pmd(pmd, __pmd(pte_val(entry)));
 
-			printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n",
-				addr, addr + PMD_SIZE - 1, p, node);
+			/* check to see if we have contiguous blocks */
+			if (p_end != p || node_start != node) {
+				if (p_start)
+					printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+						addr_start, addr_end-1, p_start, p_end-1, node_start);
+				addr_start = addr;
+				node_start = node;
+				p_start = p;
+			}
+			addr_end = addr + PMD_SIZE;
+			p_end = p + PMD_SIZE;
 		} else {
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
 		}
 	}
 	return 0;
 }
+
+void __meminit vmemmap_populate_print_last(void)
+{
+	if (p_start) {
+		printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+			addr_start, addr_end-1, p_start, p_end-1, node_start);
+		p_start = NULL;
+		p_end = NULL;
+		node_start = 0;
+	}
+}
 #endif

61 lines not on this page · raw message

index b5e02e3..71c4d68 100644
@@ -49,7 +49,7 @@ extern void update_e820(void);
 
 extern void reserve_early(unsigned long start, unsigned long end, char *name);
 extern void free_early(unsigned long start, unsigned long end);
-extern void early_res_to_bootmem(void);
+extern void early_res_to_bootmem(unsigned long start, unsigned long end);
 
 #endif/*!__ASSEMBLY__*/
 

index b695875..286d315 100644
@@ -1229,6 +1229,7 @@ void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
 int vmemmap_populate_basepages(struct page *start_page,
 						unsigned long pages, int node);
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
+void vmemmap_populate_print_last(void);
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */

282 lines not on this page · raw message

index 98d6b39..7e91913 100644
@@ -295,6 +295,9 @@ struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 	return NULL;
 }
 
+void __attribute__((weak)) __meminit vmemmap_populate_print_last(void)
+{
+}
 /*
  * Allocate the accumulated non-linear sections, allocate a mem_map
  * for each and record the physical to section mapping.

@@ -304,22 +307,50 @@ void __init sparse_init(void)
 	unsigned long pnum;
 	struct page *map;
 	unsigned long *usemap;
+	unsigned long **usemap_map;
+	int size;
+
+	/*
+	 * map is using big page (aka 2M in x86 64 bit)
+	 * usemap is less one page (aka 24 bytes)
+	 * so alloc 2M (with 2M align) and 24 bytes in turn will
+	 * make next 2M slip to one more 2M later.
+	 * then in big system, the memory will have a lot of holes...
+	 * here try to allocate 2M pages continously.
+	 *
+	 * powerpc need to call sparse_init_one_section right after each
+	 * sparse_early_mem_map_alloc, so allocate usemap_map at first.
+	 */
+	size = sizeof(unsigned long *) * NR_MEM_SECTIONS;
+	usemap_map = alloc_bootmem(size);
+	if (!usemap_map)
+		panic("can not allocate usemap_map\n");
 
 	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
 		if (!present_section_nr(pnum))
 			continue;
+		usemap_map[pnum] = sparse_early_usemap_alloc(pnum);
+	}
 
-		map = sparse_early_mem_map_alloc(pnum);
-		if (!map)
+	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+		if (!present_section_nr(pnum))
 			continue;
 
-		usemap = sparse_early_usemap_alloc(pnum);
+		usemap = usemap_map[pnum];
 		if (!usemap)
 			continue;
 
+		map = sparse_early_mem_map_alloc(pnum);
+		if (!map)
+			continue;
+
 		sparse_init_one_section(__nr_to_section(pnum), pnum, map,
 								usemap);
 	}
+
+	vmemmap_populate_print_last();
+
+	free_bootmem(__pa(usemap_map), size);
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG

Index: linux-x86.q/mm/bootmem.c
===================================================================
@@ -493,8 +493,31 @@ int __init reserve_bootmem(unsigned long
 void __init free_bootmem(unsigned long addr, unsigned long size)
 {
 	bootmem_data_t *bdata;
-	list_for_each_entry(bdata, &bdata_list, list)
-		free_bootmem_core(bdata, addr, size);
+	unsigned long pos = addr;
+	unsigned long partsize = size;
+
+	list_for_each_entry(bdata, &bdata_list, list) {
+		unsigned long remainder = 0;
+
+		if (pos < bdata->node_boot_start)
+			continue;
+
+		if (PFN_DOWN(pos + partsize) > bdata->node_low_pfn) {
+			remainder = PFN_DOWN(pos + partsize) - bdata->node_low_pfn;
+			partsize -= remainder;
+		}
+
+		free_bootmem_core(bdata, pos, partsize);
+
+		if (!remainder)
+			return;
+
+		pos = PFN_PHYS(bdata->node_low_pfn + 1);
+	}
+	printk(KERN_ERR "free_bootmem: request: addr=%lx, size=%lx, "
+			"state: pos=%lx, partsize=%lx\n", addr, size,
+			pos, partsize);
+	BUG();
 }
 
 unsigned long __init free_all_bootmem(void)

index cbd42e5..79f0d52 100644
@@ -84,6 +84,28 @@ void __init reserve_early(unsigned long start, unsigned long end, char *name)
 		strncpy(r->name, name, sizeof(r->name) - 1);
 }
 
+void __init free_early(unsigned long start, unsigned long end)
+{
+	struct early_res *r;
+	int i, j;
+
+	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
+		r = &early_res[i];
+		if (start == r->start && end == r->end)
+			break;
+	}
+	if (i >= MAX_EARLY_RES || !early_res[i].end)
+		panic("free_early on not reserved area: %lx-%lx!", start, end);
+
+	for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
+		;
+
+	memcpy(&early_res[i], &early_res[i + 1],
+	       (j - 1 - i) * sizeof(struct early_res));
+
+	early_res[j - 1].end = 0;
+}
+
 void __init early_res_to_bootmem(void)
 {
 	int i;

index d31d6b7..e25c57b 100644
@@ -11,6 +11,7 @@
 #include <linux/string.h>
 #include <linux/percpu.h>
 #include <linux/start_kernel.h>
+#include <linux/io.h>
 
 #include <asm/processor.h>
 #include <asm/proto.h>

@@ -100,6 +101,24 @@ static void __init reserve_ebda_region(void)
 	reserve_early(lowmem, 0x100000, "BIOS reserved");
 }
 
+static void __init reserve_setup_data(void)
+{
+	struct setup_data *data;
+	unsigned long pa_data;
+	char buf[32];
+
+	if (boot_params.hdr.version < 0x0209)
+		return;
+	pa_data = boot_params.hdr.setup_data;
+	while (pa_data) {
+		data = early_ioremap(pa_data, sizeof(*data));
+		sprintf(buf, "setup data %x", data->type);
+		reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf);
+		pa_data = data->next;
+		early_iounmap(data, sizeof(*data));
+	}
+}
+
 void __init x86_64_start_kernel(char * real_mode_data)
 {
 	int i;

@@ -156,6 +175,7 @@ void __init x86_64_start_kernel(char * real_mode_data)
 #endif
 
 	reserve_ebda_region();
+	reserve_setup_data();
 
 	/*
 	 * At this point everything still needed from the boot loader

193 lines not on this page · raw message

index 17bdf23..b04e2c0 100644
@@ -264,6 +264,28 @@ void __attribute__((weak)) __init memory_setup(void)
        machine_specific_memory_setup();
 }
 
+static void __init parse_setup_data(void)
+{
+	struct setup_data *data;
+	unsigned long pa_data;
+
+	if (boot_params.hdr.version < 0x0209)
+		return;
+	pa_data = boot_params.hdr.setup_data;
+	while (pa_data) {
+		data = early_ioremap(pa_data, PAGE_SIZE);
+		switch (data->type) {
+		default:
+			break;
+		}
+#ifndef CONFIG_DEBUG_BOOT_PARAMS
+		free_early(pa_data, pa_data+sizeof(*data)+data->len);
+#endif
+		pa_data = data->next;
+		early_iounmap(data, PAGE_SIZE);
+	}
+}
+
 /*
  * setup_arch - architecture-specific boot-time initializations
  *

@@ -316,6 +338,8 @@ void __init setup_arch(char **cmdline_p)
 	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = command_line;
 
+	parse_setup_data();
+
 	parse_early_param();
 
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT

index 5115135..e865990 100644
@@ -9,6 +9,17 @@
 #include <asm/ist.h>
 #include <video/edid.h>
 
+/* setup data types */
+#define SETUP_NONE			0
+
+/* extensible setup data list node */
+struct setup_data {
+	u64 next;
+	u32 type;
+	u32 len;
+	u8 data[0];
+};
+
 struct setup_header {
 	__u8	setup_sects;
 	__u16	root_flags;

@@ -46,6 +57,9 @@ struct setup_header {
 	__u32	cmdline_size;
 	__u32	hardware_subarch;
 	__u64	hardware_subarch_data;
+	__u32	payload_offset;
+	__u32	payload_length;
+	__u64	setup_data;
 } __attribute__((packed));
 
 struct sys_desc_table {

index f478c57..b5e02e3 100644
@@ -48,6 +48,7 @@ extern struct e820map e820;
 extern void update_e820(void);
 
 extern void reserve_early(unsigned long start, unsigned long end, char *name);
+extern void free_early(unsigned long start, unsigned long end);
 extern void early_res_to_bootmem(void);
 
 #endif/*!__ASSEMBLY__*/

Index: linux-x86.q/arch/x86/kernel/e820_64.c
===================================================================
@@ -100,7 +100,7 @@ void __init free_early(unsigned long sta
 	for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
 		;
 
-	memcpy(&early_res[i], &early_res[i + 1],
+	memmove(&early_res[i], &early_res[i + 1],
 	       (j - 1 - i) * sizeof(struct early_res));
 
 	early_res[j - 1].end = 0;

index 479926d..02f4dba 100644
@@ -35,6 +35,18 @@ int fallback_aper_force __initdata;
 
 int fix_aperture __initdata = 1;
 
+struct bus_dev_range {
+	int bus;
+	int dev_base;
+	int dev_limit;
+};
+
+static struct bus_dev_range bus_dev_ranges[] __initdata = {
+	{ 0x00, 0x18, 0x20},
+	{ 0xff, 0x00, 0x20},
+	{ 0xfe, 0x00, 0x20}
+};
+
 static struct resource gart_resource = {
 	.name	= "GART",
 	.flags	= IORESOURCE_MEM,

@@ -55,8 +67,9 @@ static u32 __init allocate_aperture(void)
 	u32 aper_size;
 	void *p;
 
-	if (fallback_aper_order > 7)
-		fallback_aper_order = 7;
+	/* aper_size should <= 1G */
+	if (fallback_aper_order > 5)
+		fallback_aper_order = 5;
 	aper_size = (32 * 1024 * 1024) << fallback_aper_order;
 
 	/*

@@ -65,7 +78,20 @@ static u32 __init allocate_aperture(void)
 	 * memory. Unfortunately we cannot move it up because that would
 	 * make the IOMMU useless.
 	 */
-	p = __alloc_bootmem_nopanic(aper_size, aper_size, 0);
+	/*
+	 * using 512M as goal, in case kexec will load kernel_big
+	 * that will do the on position decompress, and  could overlap with
+	 * that positon with gart that is used.
+	 * sequende:
+	 * kernel_small
+	 * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
+	 * ==> kernel_small(gart area become e820_reserved)
+	 * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
+	 * ==> kerne_big (uncompressed size will be big than 64M or 128M)
+	 * so don't use 512M below as gart iommu, leave the space for kernel
+	 * code for safe
+	 */
+	p = __alloc_bootmem_nopanic(aper_size, aper_size, 512ULL<<20);
 	if (!p || __pa(p)+aper_size > 0xffffffff) {
 		printk(KERN_ERR
 			"Cannot allocate aperture memory hole (%p,%uK)\n",

@@ -83,7 +109,7 @@ static u32 __init allocate_aperture(void)
 	return (u32)__pa(p);
 }
 
-static int __init aperture_valid(u64 aper_base, u32 aper_size)
+static int __init aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
 {
 	if (!aper_base)
 		return 0;

@@ -96,8 +122,9 @@ static int __init aperture_valid(u64 aper_base, u32 aper_size)
 		printk(KERN_ERR "Aperture pointing to e820 RAM. Ignoring.\n");
 		return 0;
 	}
-	if (aper_size < 64*1024*1024) {
-		printk(KERN_ERR "Aperture too small (%d MB)\n", aper_size>>20);
+	if (aper_size < min_size) {
+		printk(KERN_ERR "Aperture too small (%d MB) than (%d MB)\n",
+				 aper_size>>20, min_size>>20);
 		return 0;
 	}
 

@@ -105,47 +132,51 @@ static int __init aperture_valid(u64 aper_base, u32 aper_size)
 }
 
 /* Find a PCI capability */
-static __u32 __init find_cap(int num, int slot, int func, int cap)
+static __u32 __init find_cap(int bus, int slot, int func, int cap)
 {
 	int bytes;
 	u8 pos;
 
-	if (!(read_pci_config_16(num, slot, func, PCI_STATUS) &
+	if (!(read_pci_config_16(bus, slot, func, PCI_STATUS) &
 						PCI_STATUS_CAP_LIST))
 		return 0;
 
-	pos = read_pci_config_byte(num, slot, func, PCI_CAPABILITY_LIST);
+	pos = read_pci_config_byte(bus, slot, func, PCI_CAPABILITY_LIST);
 	for (bytes = 0; bytes < 48 && pos >= 0x40; bytes++) {
 		u8 id;
 
 		pos &= ~3;
-		id = read_pci_config_byte(num, slot, func, pos+PCI_CAP_LIST_ID);
+		id = read_pci_config_byte(bus, slot, func, pos+PCI_CAP_LIST_ID);
 		if (id == 0xff)
 			break;
 		if (id == cap)
 			return pos;
-		pos = read_pci_config_byte(num, slot, func,
+		pos = read_pci_config_byte(bus, slot, func,
 						pos+PCI_CAP_LIST_NEXT);
 	}
 	return 0;
 }
 
 /* Read a standard AGPv3 bridge header */
-static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
+static __u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
 {
 	u32 apsize;
 	u32 apsizereg;
 	int nbits;
 	u32 aper_low, aper_hi;
 	u64 aper;
+	u32 old_order;
 
-	printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", num, slot, func);
-	apsizereg = read_pci_config_16(num, slot, func, cap + 0x14);
+	printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", bus, slot, func);
+	apsizereg = read_pci_config_16(bus, slot, func, cap + 0x14);
 	if (apsizereg == 0xffffffff) {
 		printk(KERN_ERR "APSIZE in AGP bridge unreadable\n");
 		return 0;
 	}
 
+	/* old_order could be the value from NB gart setting */
+	old_order = *order;
+
 	apsize = apsizereg & 0xfff;
 	/* Some BIOS use weird encodings not in the AGPv3 table. */
 	if (apsize & 0xff)