15 files changed, 378 insertions, 13 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9195fd8..65a872b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -370,6 +370,7 @@ config X86_NUMACHIP
 	depends on NUMA
 	depends on SMP
 	depends on X86_X2APIC
+	depends on PCI_MMCONFIG
 	---help---
 	  Adds support for Numascale NumaChip large-SMP systems. Needed to
 	  enable more than ~168 cores.
diff --git a/arch/x86/boot/.gitignore b/arch/x86/boot/.gitignore
index 851fe93..e3cf9f6 100644
--- a/arch/x86/boot/.gitignore
+++ b/arch/x86/boot/.gitignore
@@ -2,7 +2,6 @@ bootsect
 bzImage
 cpustr.h
 mkcpustr
-offsets.h
 voffset.h
 zoffset.h
 setup
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index e87b0ca..b1942e2 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -8,6 +8,7 @@
  * ----------------------------------------------------------------------- */
 
 #include <linux/efi.h>
+#include <linux/pci.h>
 #include <asm/efi.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
@@ -245,6 +246,121 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size)
 	*size = len;
 }
 
+static efi_status_t setup_efi_pci(struct boot_params *params)
+{
+	efi_pci_io_protocol *pci;
+	efi_status_t status;
+	void **pci_handle;
+	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+	unsigned long nr_pci, size = 0;
+	int i;
+	struct setup_data *data;
+
+	data = (struct setup_data *)params->hdr.setup_data;
+
+	while (data && data->next)
+		data = (struct setup_data *)data->next;
+
+	status = efi_call_phys5(sys_table->boottime->locate_handle,
+				EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+				NULL, &size, pci_handle);
+
+	if (status == EFI_BUFFER_TOO_SMALL) {
+		status = efi_call_phys3(sys_table->boottime->allocate_pool,
+					EFI_LOADER_DATA, size, &pci_handle);
+
+		if (status != EFI_SUCCESS)
+			return status;
+
+		status = efi_call_phys5(sys_table->boottime->locate_handle,
+					EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+					NULL, &size, pci_handle);
+	}
+
+	if (status != EFI_SUCCESS)
+		goto free_handle;
+
+	nr_pci = size / sizeof(void *);
+	for (i = 0; i < nr_pci; i++) {
+		void *h = pci_handle[i];
+		uint64_t attributes;
+		struct pci_setup_rom *rom;
+
+		status = efi_call_phys3(sys_table->boottime->handle_protocol,
+					h, &pci_proto, &pci);
+
+		if (status != EFI_SUCCESS)
+			continue;
+
+		if (!pci)
+			continue;
+
+		status = efi_call_phys4(pci->attributes, pci,
+					EfiPciIoAttributeOperationGet, 0,
+					&attributes);
+
+		if (status != EFI_SUCCESS)
+			continue;
+
+		if (!attributes & EFI_PCI_IO_ATTRIBUTE_EMBEDDED_ROM)
+			continue;
+
+		if (!pci->romimage || !pci->romsize)
+			continue;
+
+		size = pci->romsize + sizeof(*rom);
+
+		status = efi_call_phys3(sys_table->boottime->allocate_pool,
+				EFI_LOADER_DATA, size, &rom);
+
+		if (status != EFI_SUCCESS)
+			continue;
+
+		rom->data.type = SETUP_PCI;
+		rom->data.len = size - sizeof(struct setup_data);
+		rom->data.next = 0;
+		rom->pcilen = pci->romsize;
+
+		status = efi_call_phys5(pci->pci.read, pci,
+					EfiPciIoWidthUint16, PCI_VENDOR_ID,
+					1, &(rom->vendor));
+
+		if (status != EFI_SUCCESS)
+			goto free_struct;
+
+		status = efi_call_phys5(pci->pci.read, pci,
+					EfiPciIoWidthUint16, PCI_DEVICE_ID,
+					1, &(rom->devid));
+
+		if (status != EFI_SUCCESS)
+			goto free_struct;
+
+		status = efi_call_phys5(pci->get_location, pci,
+					&(rom->segment), &(rom->bus),
+					&(rom->device), &(rom->function));
+
+		if (status != EFI_SUCCESS)
+			goto free_struct;
+
+		memcpy(rom->romdata, pci->romimage, pci->romsize);
+
+		if (data)
+			data->next = (uint64_t)rom;
+		else
+			params->hdr.setup_data = (uint64_t)rom;
+
+		data = (struct setup_data *)rom;
+
+		continue;
+	free_struct:
+		efi_call_phys1(sys_table->boottime->free_pool, rom);
+	}
+
+free_handle:
+	efi_call_phys1(sys_table->boottime->free_pool, pci_handle);
+	return status;
+}
+
 /*
  * See if we have Graphics Output Protocol
  */
@@ -1028,6 +1144,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
 
 	setup_graphics(boot_params);
 
+	setup_efi_pci(boot_params);
+
 	status = efi_call_phys3(sys_table->boottime->allocate_pool,
 				EFI_LOADER_DATA, sizeof(*gdt),
 				(void **)&gdt);
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index 2ad874c..92862cd 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -13,6 +13,7 @@
 #define SETUP_NONE			0
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
+#define SETUP_PCI			3
 
 /* extensible setup data list node */
 struct setup_data {
diff --git a/arch/x86/include/asm/numachip/numachip.h b/arch/x86/include/asm/numachip/numachip.h
new file mode 100644
index 0000000..1c6f7f6
--- /dev/null
+++ b/arch/x86/include/asm/numachip/numachip.h
@@ -0,0 +1,19 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Numascale NumaConnect-specific header file
+ *
+ * Copyright (C) 2012 Numascale AS. All rights reserved.
+ *
+ * Send feedback to <support@numascale.com>
+ *
+ */
+
+#ifndef _ASM_X86_NUMACHIP_NUMACHIP_H
+#define _ASM_X86_NUMACHIP_NUMACHIP_H
+
+extern int __init pci_numachip_init(void);
+
+#endif /* _ASM_X86_NUMACHIP_NUMACHIP_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 6e41b93..dba7805 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -171,4 +171,16 @@ cpumask_of_pcibus(const struct pci_bus *bus)
 }
 #endif
 
+struct pci_setup_rom {
+	struct setup_data data;
+	uint16_t vendor;
+	uint16_t devid;
+	uint64_t pcilen;
+	unsigned long segment;
+	unsigned long bus;
+	unsigned long device;
+	unsigned long function;
+	uint8_t romdata[0];
+};
+
 #endif /* _ASM_X86_PCI_H */
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index a65829a..9c2aa89 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -22,6 +22,7 @@
 #include <linux/hardirq.h>
 #include <linux/delay.h>
 
+#include <asm/numachip/numachip.h>
 #include <asm/numachip/numachip_csr.h>
 #include <asm/smp.h>
 #include <asm/apic.h>
@@ -179,6 +180,7 @@ static int __init numachip_system_init(void)
 		return 0;
 
 	x86_cpuinit.fixup_cpu_id = fixup_cpu_id;
+	x86_init.pci.arch_init = pci_numachip_init;
 
 	map_csrs();
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index e4c1a41..726bf96 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -606,7 +606,7 @@ void __init mtrr_bp_init(void)
 
 		/*
 		 * This is an AMD specific MSR, but we assume(hope?) that
-		 * Intel will implement it to when they extend the address
+		 * Intel will implement it too when they extend the address
 		 * bus of the Xeon.
 		 */
 		if (cpuid_eax(0x80000000) >= 0x80000008) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ca45696..c228322 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -143,11 +143,7 @@ int default_check_phys_apicid_present(int phys_apicid)
 }
 #endif
 
-#ifndef CONFIG_DEBUG_BOOT_PARAMS
-struct boot_params __initdata boot_params;
-#else
 struct boot_params boot_params;
-#endif
 
 /*
  * Machine setup..
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 8573b83..217eb70 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -137,7 +137,7 @@ static void pgd_dtor(pgd_t *pgd)
  * against pageattr.c; it is the unique case in which a valid change
  * of kernel pagetables can't be lazily synchronized by vmalloc faults.
  * vmalloc faults work because attached pagetables are never freed.
- * -- wli
+ * -- nyc
  */
 
 #ifdef CONFIG_X86_PAE
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 520d2bd..d11a470 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -11,6 +11,7 @@
 #include <asm/cacheflush.h>
 #include <linux/netdevice.h>
 #include <linux/filter.h>
+#include <linux/if_vlan.h>
 
 /*
  * Conventions :
@@ -212,6 +213,8 @@ void bpf_jit_compile(struct sk_filter *fp)
 		case BPF_S_ANC_MARK:
 		case BPF_S_ANC_RXHASH:
 		case BPF_S_ANC_CPU:
+		case BPF_S_ANC_VLAN_TAG:
+		case BPF_S_ANC_VLAN_TAG_PRESENT:
 		case BPF_S_ANC_QUEUE:
 		case BPF_S_LD_W_ABS:
 		case BPF_S_LD_H_ABS:
@@ -515,6 +518,24 @@ void bpf_jit_compile(struct sk_filter *fp)
 				CLEAR_A();
 #endif
 				break;
+			case BPF_S_ANC_VLAN_TAG:
+			case BPF_S_ANC_VLAN_TAG_PRESENT:
+				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
+				if (is_imm8(offsetof(struct sk_buff, vlan_tci))) {
+					/* movzwl off8(%rdi),%eax */
+					EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, vlan_tci));
+				} else {
+					EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */
+					EMIT(offsetof(struct sk_buff, vlan_tci), 4);
+				}
+				BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+				if (filter[i].code == BPF_S_ANC_VLAN_TAG) {
+					EMIT3(0x80, 0xe4, 0xef); /* and    $0xef,%ah */
+				} else {
+					EMIT3(0xc1, 0xe8, 0x0c); /* shr    $0xc,%eax */
+					EMIT3(0x83, 0xe0, 0x01); /* and    $0x1,%eax */
+				}
+				break;
 			case BPF_S_LD_W_ABS:
 				func = CHOOSE_LOAD_FUNC(K, sk_load_word);
 common_load:			seen |= SEEN_DATAREF;
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 3af5a1e..ee0af58 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_STA2X11)           += sta2x11-fixup.o
 obj-$(CONFIG_X86_VISWS)		+= visws.o
 
 obj-$(CONFIG_X86_NUMAQ)		+= numaq_32.o
+obj-$(CONFIG_X86_NUMACHIP)	+= numachip.o
 
 obj-$(CONFIG_X86_INTEL_MID)	+= mrst.o
 
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 192397c..0c01261f 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -12,6 +12,7 @@ struct pci_root_info {
 	char name[16];
 	unsigned int res_num;
 	struct resource *res;
+	resource_size_t *res_offset;
 	struct pci_sysdata sd;
 #ifdef	CONFIG_PCI_MMCONFIG
 	bool mcfg_added;
@@ -22,6 +23,7 @@ struct pci_root_info {
 };
 
 static bool pci_use_crs = true;
+static bool pci_ignore_seg = false;
 
 static int __init set_use_crs(const struct dmi_system_id *id)
 {
@@ -35,7 +37,14 @@ static int __init set_nouse_crs(const struct dmi_system_id *id)
 	return 0;
 }
 
-static const struct dmi_system_id pci_use_crs_table[] __initconst = {
+static int __init set_ignore_seg(const struct dmi_system_id *id)
+{
+	printk(KERN_INFO "PCI: %s detected: ignoring ACPI _SEG\n", id->ident);
+	pci_ignore_seg = true;
+	return 0;
+}
+
+static const struct dmi_system_id pci_crs_quirks[] __initconst = {
 	/* http://bugzilla.kernel.org/show_bug.cgi?id=14183 */
 	{
 		.callback = set_use_crs,
@@ -98,6 +107,16 @@ static const struct dmi_system_id pci_use_crs_table[] __initconst = {
 			DMI_MATCH(DMI_BIOS_VERSION, "6JET85WW (1.43 )"),
 		},
 	},
+
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=15362 */
+	{
+		.callback = set_ignore_seg,
+		.ident = "HP xw9300",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP xw9300 Workstation"),
+		},
+	},
 	{}
 };
 
@@ -108,7 +127,7 @@ void __init pci_acpi_crs_quirks(void)
 	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008)
 		pci_use_crs = false;
 
-	dmi_check_system(pci_use_crs_table);
+	dmi_check_system(pci_crs_quirks);
 
 	/*
 	 * If the user specifies "pci=use_crs" or "pci=nocrs" explicitly, that
@@ -305,6 +324,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	res->flags = flags;
 	res->start = start;
 	res->end = end;
+	info->res_offset[info->res_num] = addr.translation_offset;
 
 	if (!pci_use_crs) {
 		dev_printk(KERN_DEBUG, &info->bridge->dev,
@@ -374,7 +394,8 @@ static void add_resources(struct pci_root_info *info,
 				 "ignoring host bridge window %pR (conflicts with %s %pR)\n",
 				 res, conflict->name, conflict);
 		else
-			pci_add_resource(resources, res);
+			pci_add_resource_offset(resources, res,
+					info->res_offset[i]);
 	}
 }
 
@@ -382,6 +403,8 @@ static void free_pci_root_info_res(struct pci_root_info *info)
 {
 	kfree(info->res);
 	info->res = NULL;
+	kfree(info->res_offset);
+	info->res_offset = NULL;
 	info->res_num = 0;
 }
 
@@ -432,10 +455,20 @@ probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device,
 		return;
 
 	size = sizeof(*info->res) * info->res_num;
-	info->res_num = 0;
 	info->res = kzalloc(size, GFP_KERNEL);
-	if (!info->res)
+	if (!info->res) {
+		info->res_num = 0;
+		return;
+	}
+
+	size = sizeof(*info->res_offset) * info->res_num;
+	info->res_num = 0;
+	info->res_offset = kzalloc(size, GFP_KERNEL);
+	if (!info->res_offset) {
+		kfree(info->res);
+		info->res = NULL;
 		return;
+	}
 
 	acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource,
 				info);
@@ -455,6 +488,9 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
 	int pxm;
 #endif
 
+	if (pci_ignore_seg)
+		domain = 0;
+
 	if (domain && !pci_domains_supported) {
 		printk(KERN_WARNING "pci_bus %04x:%02x: "
 		       "ignored (multiple domains not supported)\n",
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 720e973f..1b1dda9 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -17,6 +17,7 @@
 #include <asm/io.h>
 #include <asm/smp.h>
 #include <asm/pci_x86.h>
+#include <asm/setup.h>
 
 unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 |
 				PCI_PROBE_MMCONF;
@@ -608,6 +609,35 @@ unsigned int pcibios_assign_all_busses(void)
 	return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0;
 }
 
+int pcibios_add_device(struct pci_dev *dev)
+{
+	struct setup_data *data;
+	struct pci_setup_rom *rom;
+	u64 pa_data;
+
+	pa_data = boot_params.hdr.setup_data;
+	while (pa_data) {
+		data = phys_to_virt(pa_data);
+
+		if (data->type == SETUP_PCI) {
+			rom = (struct pci_setup_rom *)data;
+
+			if ((pci_domain_nr(dev->bus) == rom->segment) &&
+			    (dev->bus->number == rom->bus) &&
+			    (PCI_SLOT(dev->devfn) == rom->device) &&
+			    (PCI_FUNC(dev->devfn) == rom->function) &&
+			    (dev->vendor == rom->vendor) &&
+			    (dev->device == rom->devid)) {
+				dev->rom = pa_data +
+				      offsetof(struct pci_setup_rom, romdata);
+				dev->romlen = rom->pcilen;
+			}
+		}
+		pa_data = data->next;
+	}
+	return 0;
+}
+
 int pcibios_enable_device(struct pci_dev *dev, int mask)
 {
 	int err;
@@ -626,7 +656,7 @@ void pcibios_disable_device (struct pci_dev *dev)
 		pcibios_disable_irq(dev);
 }
 
-int pci_ext_cfg_avail(struct pci_dev *dev)
+int pci_ext_cfg_avail(void)
 {
 	if (raw_pci_ext_ops)
 		return 1;
diff --git a/arch/x86/pci/numachip.c b/arch/x86/pci/numachip.c
new file mode 100644
index 0000000..7307d9d
--- /dev/null
+++ b/arch/x86/pci/numachip.c
@@ -0,0 +1,129 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Numascale NumaConnect-specific PCI code
+ *
+ * Copyright (C) 2012 Numascale AS. All rights reserved.
+ *
+ * Send feedback to <support@numascale.com>
+ *
+ * PCI accessor functions derived from mmconfig_64.c
+ *
+ */
+
+#include <linux/pci.h>
+#include <asm/pci_x86.h>
+
+static u8 limit __read_mostly;
+
+static inline char __iomem *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn)
+{
+	struct pci_mmcfg_region *cfg = pci_mmconfig_lookup(seg, bus);
+
+	if (cfg && cfg->virt)
+		return cfg->virt + (PCI_MMCFG_BUS_OFFSET(bus) | (devfn << 12));
+	return NULL;
+}
+
+static int pci_mmcfg_read_numachip(unsigned int seg, unsigned int bus,
+			  unsigned int devfn, int reg, int len, u32 *value)
+{
+	char __iomem *addr;
+
+	/* Why do we have this when nobody checks it. How about a BUG()!? -AK */
+	if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095))) {
+err:		*value = -1;
+		return -EINVAL;
+	}
+
+	/* Ensure AMD Northbridges don't decode reads to other devices */
+	if (unlikely(bus == 0 && devfn >= limit)) {
+		*value = -1;
+		return 0;
+	}
+
+	rcu_read_lock();
+	addr = pci_dev_base(seg, bus, devfn);
+	if (!addr) {
+		rcu_read_unlock();
+		goto err;
+	}
+
+	switch (len) {
+	case 1:
+		*value = mmio_config_readb(addr + reg);
+		break;
+	case 2:
+		*value = mmio_config_readw(addr + reg);
+		break;
+	case 4:
+		*value = mmio_config_readl(addr + reg);
+		break;
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int pci_mmcfg_write_numachip(unsigned int seg, unsigned int bus,
+			   unsigned int devfn, int reg, int len, u32 value)
+{
+	char __iomem *addr;
+
+	/* Why do we have this when nobody checks it. How about a BUG()!? -AK */
+	if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095)))
+		return -EINVAL;
+
+	/* Ensure AMD Northbridges don't decode writes to other devices */
+	if (unlikely(bus == 0 && devfn >= limit))
+		return 0;
+
+	rcu_read_lock();
+	addr = pci_dev_base(seg, bus, devfn);
+	if (!addr) {
+		rcu_read_unlock();
+		return -EINVAL;
+	}
+
+	switch (len) {
+	case 1:
+		mmio_config_writeb(addr + reg, value);
+		break;
+	case 2:
+		mmio_config_writew(addr + reg, value);
+		break;
+	case 4:
+		mmio_config_writel(addr + reg, value);
+		break;
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+
+const struct pci_raw_ops pci_mmcfg_numachip = {
+	.read = pci_mmcfg_read_numachip,
+	.write = pci_mmcfg_write_numachip,
+};
+
+int __init pci_numachip_init(void)
+{
+	int ret = 0;
+	u32 val;
+
+	/* For remote I/O, restrict bus 0 access to the actual number of AMD
+	   Northbridges, which starts at device number 0x18 */
+	ret = raw_pci_read(0, 0, PCI_DEVFN(0x18, 0), 0x60, sizeof(val), &val);
+	if (ret)
+		goto out;
+
+	/* HyperTransport fabric size in bits 6:4 */
+	limit = PCI_DEVFN(0x18 + ((val >> 4) & 7) + 1, 0);
+
+	/* Use NumaChip PCI accessors for non-extended and extended access */
+	raw_pci_ops = raw_pci_ext_ops = &pci_mmcfg_numachip;
+out:
+	return ret;
+}