Merge wailua.hpl.hp.com:/bk/vanilla/linux-2.5

into wailua.hpl.hp.com:/bk/lia64/to-linus-2.5

arch/ia64/Config.help

@@ -414,12 +414,18 @@ CONFIG_IA64_GENERIC
 
   HP-simulator   For the HP simulator
                  (<http://software.hp.com/ia64linux/>).
+  HP-zx1         For HP zx1 platforms.
   SN1-simulator  For the SGI SN1 simulator.
   DIG-compliant  For DIG ("Developer's Interface Guide") compliant
-                 system.
+                 systems.
 
   If you don't know what to do, choose "generic".
 
+CONFIG_IA64_HP_ZX1
+  Build a kernel that runs on HP zx1-based systems.  This adds support
+  for the zx1 IOMMU and makes root bus bridges appear in PCI config space
+  (required for zx1 agpgart support).
+
 CONFIG_IA64_PAGE_SIZE_4KB
   This lets you select the page size of the kernel.  For best IA-64
   performance, a page size of 8KB or 16KB is recommended.  For best
@@ -440,6 +446,32 @@ CONFIG_ITANIUM_BSTEP_SPECIFIC
   with a B-step CPU.  You have a B-step CPU if the "revision" field in
   /proc/cpuinfo has a value in the range from 1 to 4.
 
+CONFIG_IA64_SGI_AUTOTEST
+  Build a kernel used for hardware validation. If you include the
+  keyword "autotest" on the boot command line, the kernel does NOT boot.
+  Instead, it starts all cpus and runs cache coherency tests instead.
+
+  If unsure, say N.
+
+CONFIG_IA64_SGI_SN_DEBUG
+  Turns on extra debugging code in the SGI SN (Scalable NUMA) platform
+  for IA64.  Unless you are debugging problems on an SGI SN IA64 box,
+  say N.
+
+CONFIG_IA64_SGI_SN_SIM
+  If you are compiling a kernel that will run under SGI's IA64
+  simulator (Medusa) then say Y, otherwise say N.
+
+CONFIG_SERIAL_SGI_L1_PROTOCOL
+  Uses protocol mode instead of raw mode for the level 1 console on the
+  SGI SN (Scalable NUMA) platform for IA64.  If you are compiling for
+  an SGI SN box then Y is the recommended value, otherwise say N.
+
+CONFIG_PCIBA
+  IRIX PCIBA-inspired user mode PCI interface for the SGI SN (Scalable
+  NUMA) platform for IA64.  Unless you are compiling a kernel for an
+  SGI SN IA64 box, say N.
+
 CONFIG_IA64_MCA
   Say Y here to enable machine check support for IA-64.  If you're
   unsure, answer Y.

arch/ia64/Makefile

@@ -22,7 +22,7 @@ CFLAGS := $(CFLAGS) -pipe $(EXTRA) -ffixed-r13 -mfixed-range=f10-f15,f32-f127 \
 # -ffunction-sections
 CFLAGS_KERNEL := -mconstant-gp
 
-GCC_VERSION=$(shell $(CROSS_COMPILE)$(HOSTCC) -v 2>&1 | fgrep 'gcc version' | cut -f3 -d' ' | cut -f1 -d'.')
+GCC_VERSION=$(shell $(CC) -v 2>&1 | fgrep 'gcc version' | cut -f3 -d' ' | cut -f1 -d'.')
 
 ifneq ($(GCC_VERSION),2)
 	CFLAGS += -frename-registers --param max-inline-insns=2000
@@ -33,16 +33,11 @@ ifeq ($(CONFIG_ITANIUM_BSTEP_SPECIFIC),y)
 endif
 
 ifdef CONFIG_IA64_GENERIC
-	CORE_FILES      :=      arch/$(ARCH)/hp/hp.a	\
-				arch/$(ARCH)/sn/sn.o	\
+	CORE_FILES      :=      arch/$(ARCH)/hp/hp.o			\
 				arch/$(ARCH)/dig/dig.a			\
-				arch/$(ARCH)/sn/io/sgiio.o \
 				$(CORE_FILES)
 	SUBDIRS		:=	arch/$(ARCH)/hp		\
-				arch/$(ARCH)/sn/sn1	\
-				arch/$(ARCH)/sn		\
 				arch/$(ARCH)/dig	\
-				arch/$(ARCH)/sn/io	\
 				$(SUBDIRS)
 
 else # !GENERIC
@@ -50,7 +45,16 @@ else # !GENERIC
 ifdef CONFIG_IA64_HP_SIM
         SUBDIRS         :=      arch/$(ARCH)/hp		\
                                 $(SUBDIRS)
-        CORE_FILES      :=      arch/$(ARCH)/hp/hp.a	\
+        CORE_FILES      :=      arch/$(ARCH)/hp/hp.o	\
+                                $(CORE_FILES)
+endif
+
+ifdef CONFIG_IA64_HP_ZX1
+        SUBDIRS         :=      arch/$(ARCH)/hp				\
+				arch/$(ARCH)/dig			\
+                                $(SUBDIRS)
+        CORE_FILES      :=      arch/$(ARCH)/hp/hp.o			\
+				arch/$(ARCH)/dig/dig.a			\
                                 $(CORE_FILES)
 endif
 

arch/ia64/config.in

@@ -22,6 +22,7 @@ choice 'IA-64 system type'					\
 	"generic		CONFIG_IA64_GENERIC		\
 	 DIG-compliant		CONFIG_IA64_DIG			\
 	 HP-simulator		CONFIG_IA64_HP_SIM		\
+	 HP-zx1			CONFIG_IA64_HP_ZX1		\
 	 SGI-SN1		CONFIG_IA64_SGI_SN1		\
 	 SGI-SN2		CONFIG_IA64_SGI_SN2" generic
 
@@ -56,7 +57,7 @@ if [ "$CONFIG_MCKINLEY" = "y" ]; then
 	fi
 fi
 
-if [ "$CONFIG_IA64_DIG" = "y" ]; then
+if [ "$CONFIG_IA64_GENERIC" = "y" ] || [ "$CONFIG_IA64_DIG" = "y" ] || [ "$CONFIG_IA64_HP_ZX1" = "y" ]; then
 	bool '  Enable IA-64 Machine Check Abort' CONFIG_IA64_MCA
 	define_bool CONFIG_PM y
 fi

arch/ia64/defconfig

@@ -23,7 +23,7 @@ CONFIG_MODVERSIONS=y
 # CONFIG_KMOD is not set
 
 #
-# General setup
+# Processor type and features
 #
 CONFIG_IA64=y
 # CONFIG_ISA is not set
@@ -32,21 +32,22 @@ CONFIG_IA64=y
 # CONFIG_SBUS is not set
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 # CONFIG_RWSEM_XCHGADD_ALGORITHM is not set
-CONFIG_ACPI=y
-CONFIG_ACPI_EFI=y
-CONFIG_ACPI_INTERPRETER=y
-CONFIG_ACPI_KERNEL_CONFIG=y
 CONFIG_ITANIUM=y
 # CONFIG_MCKINLEY is not set
 # CONFIG_IA64_GENERIC is not set
 CONFIG_IA64_DIG=y
 # CONFIG_IA64_HP_SIM is not set
+# CONFIG_IA64_HP_ZX1 is not set
 # CONFIG_IA64_SGI_SN1 is not set
 # CONFIG_IA64_SGI_SN2 is not set
 # CONFIG_IA64_PAGE_SIZE_4KB is not set
 # CONFIG_IA64_PAGE_SIZE_8KB is not set
 CONFIG_IA64_PAGE_SIZE_16KB=y
 # CONFIG_IA64_PAGE_SIZE_64KB is not set
+CONFIG_ACPI=y
+CONFIG_ACPI_EFI=y
+CONFIG_ACPI_INTERPRETER=y
+CONFIG_ACPI_KERNEL_CONFIG=y
 CONFIG_IA64_BRL_EMU=y
 # CONFIG_ITANIUM_BSTEP_SPECIFIC is not set
 CONFIG_IA64_L1_CACHE_SHIFT=6
@@ -60,15 +61,23 @@ CONFIG_IA64_PALINFO=y
 CONFIG_EFI_VARS=y
 CONFIG_BINFMT_ELF=y
 # CONFIG_BINFMT_MISC is not set
-# CONFIG_ACPI_DEBUG is not set
-CONFIG_ACPI_BUSMGR=y
-CONFIG_ACPI_SYS=y
-CONFIG_ACPI_CPU=y
+
+#
+# ACPI Support
+#
+CONFIG_ACPI=y
+CONFIG_ACPI_EFI=y
+CONFIG_ACPI_BOOT=y
+CONFIG_ACPI_BUS=y
+CONFIG_ACPI_INTERPRETER=y
+CONFIG_ACPI_PCI=y
+CONFIG_ACPI_POWER=y
+CONFIG_ACPI_SYSTEM=y
 CONFIG_ACPI_BUTTON=y
-CONFIG_ACPI_AC=y
-CONFIG_ACPI_EC=y
-CONFIG_ACPI_CMBATT=y
-CONFIG_ACPI_THERMAL=y
+CONFIG_ACPI_FAN=m
+CONFIG_ACPI_PROCESSOR=m
+CONFIG_ACPI_THERMAL=m
+# CONFIG_ACPI_DEBUG is not set
 CONFIG_PCI=y
 CONFIG_PCI_NAMES=y
 # CONFIG_HOTPLUG is not set
@@ -231,15 +240,13 @@ CONFIG_BLK_DEV_IDEDMA=y
 # CONFIG_BLK_DEV_ALI15X3 is not set
 # CONFIG_WDC_ALI15X3 is not set
 # CONFIG_BLK_DEV_AMD74XX is not set
-# CONFIG_AMD74XX_OVERRIDE is not set
 # CONFIG_BLK_DEV_CMD64X is not set
 # CONFIG_BLK_DEV_CY82C693 is not set
 # CONFIG_BLK_DEV_CS5530 is not set
 # CONFIG_BLK_DEV_HPT34X is not set
 # CONFIG_HPT34X_AUTODMA is not set
 # CONFIG_BLK_DEV_HPT366 is not set
-CONFIG_BLK_DEV_PIIX=y
-# CONFIG_PIIX_TUNING is not set
+# CONFIG_BLK_DEV_PIIX is not set
 # CONFIG_BLK_DEV_NS87415 is not set
 # CONFIG_BLK_DEV_OPTI621 is not set
 # CONFIG_BLK_DEV_PDC_ADMA is not set
@@ -254,7 +261,6 @@ CONFIG_BLK_DEV_PIIX=y
 # CONFIG_IDEDMA_IVB is not set
 # CONFIG_IDEDMA_AUTO is not set
 # CONFIG_DMA_NONPCI is not set
-CONFIG_BLK_DEV_IDE_MODES=y
 # CONFIG_BLK_DEV_ATARAID is not set
 # CONFIG_BLK_DEV_ATARAID_PDC is not set
 # CONFIG_BLK_DEV_ATARAID_HPT is not set
@@ -691,8 +697,6 @@ CONFIG_MSDOS_PARTITION=y
 # CONFIG_MINIX_SUBPARTITION is not set
 # CONFIG_SOLARIS_X86_PARTITION is not set
 # CONFIG_UNIXWARE_DISKLABEL is not set
-CONFIG_EFI_PARTITION=y
-# CONFIG_DEVFS_GUID is not set
 # CONFIG_LDM_PARTITION is not set
 # CONFIG_SGI_PARTITION is not set
 # CONFIG_ULTRIX_PARTITION is not set
@@ -726,6 +730,7 @@ CONFIG_NLS_DEFAULT="iso8859-1"
 # CONFIG_NLS_CODEPAGE_949 is not set
 # CONFIG_NLS_CODEPAGE_874 is not set
 # CONFIG_NLS_ISO8859_8 is not set
+# CONFIG_NLS_CODEPAGE_1250 is not set
 # CONFIG_NLS_CODEPAGE_1251 is not set
 # CONFIG_NLS_ISO8859_1 is not set
 # CONFIG_NLS_ISO8859_2 is not set
@@ -814,8 +819,9 @@ CONFIG_USB_UHCI=m
 # USB Device Class drivers
 #
 # CONFIG_USB_AUDIO is not set
-# CONFIG_USB_EMI26 is not set
-# CONFIG_USB_BLUETOOTH is not set
+# CONFIG_USB_BLUETOOTH_TTY is not set
+# CONFIG_USB_ACM is not set
+# CONFIG_USB_PRINTER is not set
 # CONFIG_USB_STORAGE is not set
 # CONFIG_USB_STORAGE_DEBUG is not set
 # CONFIG_USB_STORAGE_DATAFAB is not set
@@ -825,13 +831,12 @@ CONFIG_USB_UHCI=m
 # CONFIG_USB_STORAGE_HP8200e is not set
 # CONFIG_USB_STORAGE_SDDR09 is not set
 # CONFIG_USB_STORAGE_JUMPSHOT is not set
-# CONFIG_USB_ACM is not set
-# CONFIG_USB_PRINTER is not set
 
 #
 # USB Human Interface Devices (HID)
 #
 CONFIG_USB_HID=m
+CONFIG_USB_HIDINPUT=y
 CONFIG_USB_HIDDEV=y
 CONFIG_USB_KBD=m
 CONFIG_USB_MOUSE=m
@@ -849,23 +854,24 @@ CONFIG_USB_MOUSE=m
 #
 # USB Multimedia devices
 #
+# CONFIG_USB_DABUSB is not set
+# CONFIG_USB_VICAM is not set
+# CONFIG_USB_DSBR is not set
 # CONFIG_USB_IBMCAM is not set
+# CONFIG_USB_KONICAWC is not set
 # CONFIG_USB_OV511 is not set
 # CONFIG_USB_PWC is not set
 # CONFIG_USB_SE401 is not set
 # CONFIG_USB_STV680 is not set
-# CONFIG_USB_VICAM is not set
-# CONFIG_USB_DSBR is not set
-# CONFIG_USB_DABUSB is not set
-# CONFIG_USB_KONICAWC is not set
 
 #
 # USB Network adaptors
 #
-# CONFIG_USB_PEGASUS is not set
-# CONFIG_USB_KAWETH is not set
 # CONFIG_USB_CATC is not set
 # CONFIG_USB_CDCETHER is not set
+# CONFIG_USB_KAWETH is not set
+# CONFIG_USB_PEGASUS is not set
+# CONFIG_USB_RTL8150 is not set
 # CONFIG_USB_USBNET is not set
 
 #
@@ -897,9 +903,11 @@ CONFIG_USB_MOUSE=m
 # CONFIG_USB_SERIAL_KEYSPAN_USA18X is not set
 # CONFIG_USB_SERIAL_KEYSPAN_USA19W is not set
 # CONFIG_USB_SERIAL_KEYSPAN_USA49W is not set
-# CONFIG_USB_SERIAL_MCT_U232 is not set
 # CONFIG_USB_SERIAL_KLSI is not set
+# CONFIG_USB_SERIAL_MCT_U232 is not set
 # CONFIG_USB_SERIAL_PL2303 is not set
+# CONFIG_USB_SERIAL_SAFE is not set
+# CONFIG_USB_SERIAL_SAFE_PADDED is not set
 # CONFIG_USB_SERIAL_CYBERJACK is not set
 # CONFIG_USB_SERIAL_XIRCOM is not set
 # CONFIG_USB_SERIAL_OMNINET is not set
@@ -907,8 +915,10 @@ CONFIG_USB_MOUSE=m
 #
 # USB Miscellaneous drivers
 #
-# CONFIG_USB_RIO500 is not set
+# CONFIG_USB_EMI26 is not set
+# CONFIG_USB_TIGL is not set
 # CONFIG_USB_AUERSWALD is not set
+# CONFIG_USB_RIO500 is not set
 
 #
 # Library routines
@@ -936,11 +946,3 @@ CONFIG_IA64_EARLY_PRINTK=y
 # CONFIG_DEBUG_SPINLOCK is not set
 # CONFIG_IA64_DEBUG_CMPXCHG is not set
 # CONFIG_IA64_DEBUG_IRQ is not set
-CONFIG_KDB=y
-# CONFIG_KDB_MODULES is not set
-# CONFIG_KDB_OFF is not set
-
-#
-#   Load all symbols for debugging is required for KDB
-#
-CONFIG_KALLSYMS=y

arch/ia64/dig/setup.c

@@ -33,9 +33,6 @@
  * is sufficient (the IDE driver will autodetect the drive geometry).
  */
 char drive_info[4*16];
-extern int pcat_compat;
-
-unsigned char aux_device_present = 0xaa;	/* XXX remove this when legacy I/O is gone */
 
 void __init
 dig_setup (char **cmdline_p)
@@ -85,16 +82,4 @@ dig_setup (char **cmdline_p)
 void __init
 dig_irq_init (void)
 {
-	if (pcat_compat) {
-		/*
-		 * Disable the compatibility mode interrupts (8259 style), needs IN/OUT support
-		 * enabled.
-		 */
-		printk("%s: Disabling PC-AT compatible 8259 interrupts\n", __FUNCTION__);
-		outb(0xff, 0xA1);
-		outb(0xff, 0x21);
-	} else {
-		printk("%s: System doesn't have PC-AT compatible dual-8259 setup. "
-		       "Nothing to be done\n", __FUNCTION__);
-	}
 }

arch/ia64/hp/Config.in

+mainmenu_option next_comment
+comment 'HP Simulator drivers'
+
+bool 'Simulated Ethernet ' CONFIG_HP_SIMETH
+bool 'Simulated serial driver support' CONFIG_HP_SIMSERIAL
+if [ "$CONFIG_SCSI" != "n" ]; then
+  bool 'Simulated SCSI disk' CONFIG_HP_SIMSCSI
+fi
+endmenu

arch/ia64/hp/Makefile

-#
-# ia64/platform/hp/Makefile
-#
-# Copyright (C) 2002 Hewlett-Packard Co.
-#	David Mosberger-Tang <davidm@hpl.hp.com>
-# Copyright (C) 1999 Silicon Graphics, Inc.
-# Copyright (C) Srinivasa Thirumalachar (sprasad@engr.sgi.com)
-#
+# arch/ia64/hp/Makefile
+# Copyright (c) 2002 Matthew Wilcox for Hewlett Packard
 
-all: hp.a
+ALL_SUB_DIRS := sim zx1 common
 
-O_TARGET := hp.a
+O_TARGET := hp.o
 
-obj-y := hpsim_console.o hpsim_irq.o hpsim_setup.o
-obj-$(CONFIG_IA64_GENERIC) += hpsim_machvec.o
+subdir-$(CONFIG_IA64_GENERIC) += $(ALL_SUB_DIRS)
+subdir-$(CONFIG_IA64_HP_SIM) += sim
+subdir-$(CONFIG_IA64_HP_ZX1) += zx1 common
 
-obj-$(CONFIG_SIMETH)	+= simeth.o
-obj-$(CONFIG_SIM_SERIAL) += simserial.o
-obj-$(CONFIG_SCSI_SIM)	+= simscsi.o
-
-clean::
+SUB_DIRS := $(subdir-y)
+obj-y += $(join $(subdir-y),$(subdir-y:%=/%.o))
 
 include $(TOPDIR)/Rules.make

arch/ia64/hp/common/Makefile

+#
+# ia64/platform/hp/common/Makefile
+#
+# Copyright (C) 2002 Hewlett Packard
+# Copyright (C) Alex Williamson (alex_williamson@hp.com)
+#
+
+O_TARGET := common.o
+
+export-objs := sba_iommu.o
+
+obj-y := sba_iommu.o
+
+include $(TOPDIR)/Rules.make
+#
+# ia64/platform/hp/common/Makefile
+#
+# Copyright (C) 2002 Hewlett Packard
+# Copyright (C) Alex Williamson (alex_williamson@hp.com)
+#
+
+O_TARGET := common.o
+
+export-objs := sba_iommu.o
+
+obj-y := sba_iommu.o
+
+include $(TOPDIR)/Rules.make

arch/ia64/hp/sim/Makefile

+#
+# ia64/platform/hp/sim/Makefile
+#
+# Copyright (C) 2002 Hewlett-Packard Co.
+#	David Mosberger-Tang <davidm@hpl.hp.com>
+# Copyright (C) 1999 Silicon Graphics, Inc.
+# Copyright (C) Srinivasa Thirumalachar (sprasad@engr.sgi.com)
+#
+
+O_TARGET := sim.o
+
+obj-y := hpsim_console.o hpsim_irq.o hpsim_setup.o
+obj-$(CONFIG_IA64_GENERIC) += hpsim_machvec.o
+
+obj-$(CONFIG_HP_SIMETH)	+= simeth.o
+obj-$(CONFIG_HP_SIMSERIAL) += simserial.o
+obj-$(CONFIG_HP_SIMSCSI) += simscsi.o
+
+include $(TOPDIR)/Rules.make

arch/ia64/hp/zx1/Makefile

+#
+# ia64/platform/hp/zx1/Makefile
+#
+# Copyright (C) 2002 Hewlett Packard
+# Copyright (C) Alex Williamson (alex_williamson@hp.com)
+#
+
+O_TARGET := zx1.o
+
+obj-y := hpzx1_misc.o
+obj-$(CONFIG_IA64_GENERIC) += hpzx1_machvec.o
+
+include $(TOPDIR)/Rules.make
+#
+# ia64/platform/hp/zx1/Makefile
+#
+# Copyright (C) 2002 Hewlett Packard
+# Copyright (C) Alex Williamson (alex_williamson@hp.com)
+#
+
+O_TARGET := zx1.o
+
+obj-y := hpzx1_misc.o
+obj-$(CONFIG_IA64_GENERIC) += hpzx1_machvec.o
+
+include $(TOPDIR)/Rules.make

arch/ia64/hp/zx1/hpzx1_machvec.c

+#define MACHVEC_PLATFORM_NAME	hpzx1
+#include <asm/machvec_init.h>
+#define MACHVEC_PLATFORM_NAME	hpzx1
+#include <asm/machvec_init.h>

arch/ia64/ia32/binfmt_elf32.c

@@ -47,6 +47,8 @@ static void elf32_set_personality (void);
 #define ELF_PLAT_INIT(_r)		ia64_elf32_init(_r)
 #define setup_arg_pages(bprm)		ia32_setup_arg_pages(bprm)
 #define elf_map				elf32_map
+
+#undef SET_PERSONALITY
 #define SET_PERSONALITY(ex, ibcs2)	elf32_set_personality()
 
 /* Ugly but avoids duplication */

arch/ia64/ia32/sys_ia32.c

@@ -3003,7 +3003,7 @@ sys32_ptrace (int request, pid_t pid, unsigned int addr, unsigned int data,
 		if (request != PTRACE_KILL)
 			goto out;
 	}
-	if (child->p_pptr != current)
+	if (child->parent != current)
 		goto out;
 
 	switch (request) {

arch/ia64/kernel/Makefile

@@ -17,6 +17,7 @@ obj-y := acpi.o entry.o gate.o efi.o efi_stub.o ia64_ksyms.o irq.o irq_ia64.o ir
 	 machvec.o pal.o process.o perfmon.o ptrace.o sal.o semaphore.o setup.o	\
 	 signal.o sys_ia64.o traps.o time.o unaligned.o unwind.o
 obj-$(CONFIG_IA64_GENERIC) += iosapic.o
+obj-$(CONFIG_IA64_HP_ZX1) += iosapic.o
 obj-$(CONFIG_IA64_DIG) += iosapic.o
 obj-$(CONFIG_IA64_PALINFO) += palinfo.o
 obj-$(CONFIG_EFI_VARS) += efivars.o

arch/ia64/kernel/brl_emu.c

@@ -55,7 +55,7 @@ struct illegal_op_return
 ia64_emulate_brl (struct pt_regs *regs, unsigned long ar_ec)
 {
 	unsigned long bundle[2];
-	unsigned long opcode, btype, qp, offset;
+	unsigned long opcode, btype, qp, offset, cpl;
 	unsigned long next_ip;
 	struct siginfo siginfo;
 	struct illegal_op_return rv;
@@ -158,9 +158,9 @@ ia64_emulate_brl (struct pt_regs *regs, unsigned long ar_ec)
 			 *  AR[PFS].pec = AR[EC]
 			 *  AR[PFS].ppl = PSR.cpl
 			 */
+			cpl = ia64_psr(regs)->cpl;
 			regs->ar_pfs = ((regs->cr_ifs & 0x3fffffffff)
-					| (ar_ec << 52)
-					| ((unsigned long) ia64_psr(regs)->cpl << 62));
+					| (ar_ec << 52) | (cpl << 62));
 
 			/*
 			 *  CFM.sof -= CFM.sol

arch/ia64/kernel/efi.c

@@ -155,10 +155,10 @@ efi_memmap_walk (efi_freemem_callback_t callback, void *arg)
 		      case EFI_CONVENTIONAL_MEMORY:
 			if (!(md->attribute & EFI_MEMORY_WB))
 				continue;
-			if (md->phys_addr + (md->num_pages << 12) > mem_limit) {
+			if (md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) > mem_limit) {
 				if (md->phys_addr > mem_limit)
 					continue;
-				md->num_pages = (mem_limit - md->phys_addr) >> 12;
+				md->num_pages = (mem_limit - md->phys_addr) >> EFI_PAGE_SHIFT;
 			}
 			if (md->num_pages == 0) {
 				printk("efi_memmap_walk: ignoring empty region at 0x%lx",
@@ -167,7 +167,7 @@ efi_memmap_walk (efi_freemem_callback_t callback, void *arg)
 			}
 
 			curr.start = PAGE_OFFSET + md->phys_addr;
-			curr.end   = curr.start + (md->num_pages << 12);
+			curr.end   = curr.start + (md->num_pages << EFI_PAGE_SHIFT);
 
 			if (!prev_valid) {
 				prev = curr;
@@ -250,16 +250,17 @@ efi_map_pal_code (void)
 		 * dedicated ITR for the PAL code.
 		 */
 		if ((vaddr & mask) == (KERNEL_START & mask)) {
-			printk(__FUNCTION__ ": no need to install ITR for PAL code\n");
+			printk("%s: no need to install ITR for PAL code\n", __FUNCTION__);
 			continue;
 		}
 
-		if (md->num_pages << 12 > IA64_GRANULE_SIZE)
+		if (md->num_pages << EFI_PAGE_SHIFT > IA64_GRANULE_SIZE)
 			panic("Woah!  PAL code size bigger than a granule!");
 
 		mask  = ~((1 << IA64_GRANULE_SHIFT) - 1);
 		printk("CPU %d: mapping PAL code [0x%lx-0x%lx) into [0x%lx-0x%lx)\n",
-		       smp_processor_id(), md->phys_addr, md->phys_addr + (md->num_pages << 12),
+		       smp_processor_id(), md->phys_addr,
+		       md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT),
 		       vaddr & mask, (vaddr & mask) + IA64_GRANULE_SIZE);
 
 		/*
@@ -375,7 +376,8 @@ efi_init (void)
 			md = p;
 			printk("mem%02u: type=%u, attr=0x%lx, range=[0x%016lx-0x%016lx) (%luMB)\n",
 			       i, md->type, md->attribute, md->phys_addr,
-			       md->phys_addr + (md->num_pages<<12) - 1, md->num_pages >> 8);
+			       md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1,
+			       md->num_pages >> (20 - EFI_PAGE_SHIFT));
 		}
 	}
 #endif
@@ -482,8 +484,50 @@ efi_get_iobase (void)
 	return 0;
 }
 
+u32
+efi_mem_type (u64 phys_addr)
+{
+	void *efi_map_start, *efi_map_end, *p;
+	efi_memory_desc_t *md;
+	u64 efi_desc_size;
+
+	efi_map_start = __va(ia64_boot_param->efi_memmap);
+	efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
+	efi_desc_size = ia64_boot_param->efi_memdesc_size;
+
+	for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
+		md = p;
+
+		if ((md->phys_addr <= phys_addr) && (phys_addr <=
+		    (md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1)))
+			 return md->type;
+	}
+	return 0;
+}
+
+u64
+efi_mem_attributes (u64 phys_addr)
+{
+	void *efi_map_start, *efi_map_end, *p;
+	efi_memory_desc_t *md;
+	u64 efi_desc_size;
+
+	efi_map_start = __va(ia64_boot_param->efi_memmap);
+	efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
+	efi_desc_size = ia64_boot_param->efi_memdesc_size;
+
+	for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
+		md = p;
+
+		if ((md->phys_addr <= phys_addr) && (phys_addr <=
+		    (md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1)))
+			return md->attribute;
+	}
+	return 0;
+}
+
 static void __exit
-efivars_exit(void)
+efivars_exit (void)
 {
 #ifdef CONFIG_PROC_FS
  	remove_proc_entry(efi_dir->name, NULL);

arch/ia64/kernel/entry.S

@@ -36,6 +36,7 @@
 #include <asm/kregs.h>
 #include <asm/offsets.h>
 #include <asm/pgtable.h>
+#include <asm/percpu.h>
 #include <asm/processor.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
@@ -214,61 +215,79 @@ GLOBAL_ENTRY(save_switch_stack)
 	.save @priunat,r17
 	mov r17=ar.unat		// preserve caller's
 	.body
-	adds r3=80,sp
+#ifdef CONFIG_ITANIUM
+	adds r2=16+128,sp
+	adds r3=16+64,sp
+	adds r14=SW(R4)+16,sp
 	;;
+	st8.spill [r14]=r4,16		// spill r4
 	lfetch.fault.excl.nt1 [r3],128
-	mov ar.rsc=0		// put RSE in mode: enforced lazy, little endian, pl 0
-	adds r2=16+128,sp
 	;;
 	lfetch.fault.excl.nt1 [r2],128
 	lfetch.fault.excl.nt1 [r3],128
-	adds r14=SW(R4)+16,sp
 	;;
 	lfetch.fault.excl [r2]
 	lfetch.fault.excl [r3]
 	adds r15=SW(R5)+16,sp
+#else
+	add r2=16+3*128,sp
+	add r3=16,sp
+	add r14=SW(R4)+16,sp
+	;;
+	st8.spill [r14]=r4,SW(R6)-SW(R4)	// spill r4 and prefetch offset 0x1c0
+	lfetch.fault.excl.nt1 [r3],128	//		prefetch offset 0x010
+	;;
+	lfetch.fault.excl.nt1 [r3],128	//		prefetch offset 0x090
+	lfetch.fault.excl.nt1 [r2],128	//		prefetch offset 0x190
+	;;
+	lfetch.fault.excl.nt1 [r3]	//		prefetch offset 0x110
+	lfetch.fault.excl.nt1 [r2]	//		prefetch offset 0x210
+	adds r15=SW(R5)+16,sp
+#endif
 	;;
-	mov r18=ar.fpsr		// preserve fpsr
-	mov r19=ar.rnat
+	st8.spill [r15]=r5,SW(R7)-SW(R5)	// spill r5
+	mov.m ar.rsc=0			// put RSE in mode: enforced lazy, little endian, pl 0
 	add r2=SW(F2)+16,sp		// r2 = &sw->f2
-.mem.offset 0,0; st8.spill [r14]=r4,16		// spill r4
-.mem.offset 8,0; st8.spill [r15]=r5,16		// spill r5
+	;;
+	st8.spill [r14]=r6,SW(B0)-SW(R6)	// spill r6
+	mov.m r18=ar.fpsr		// preserve fpsr
 	add r3=SW(F3)+16,sp		// r3 = &sw->f3
 	;;
 	stf.spill [r2]=f2,32
-	stf.spill [r3]=f3,32
+	mov.m r19=ar.rnat
 	mov r21=b0
-.mem.offset 0,0; st8.spill [r14]=r6,16		// spill r6
-.mem.offset 8,0; st8.spill [r15]=r7,16		// spill r7
+
+	stf.spill [r3]=f3,32
+	st8.spill [r15]=r7,SW(B2)-SW(R7)	// spill r7
 	mov r22=b1
 	;;
 	// since we're done with the spills, read and save ar.unat:
-	mov r29=ar.unat		// M-unit
-	mov r20=ar.bspstore	// M-unit
+	mov.m r29=ar.unat
+	mov.m r20=ar.bspstore
 	mov r23=b2
 	stf.spill [r2]=f4,32
 	stf.spill [r3]=f5,32
 	mov r24=b3
 	;;
-	st8 [r14]=r21,16	// save b0
-	st8 [r15]=r22,16	// save b1
+	st8 [r14]=r21,SW(B1)-SW(B0)		// save b0
+	st8 [r15]=r23,SW(B3)-SW(B2)		// save b2
 	mov r25=b4
 	stf.spill [r2]=f10,32
 	stf.spill [r3]=f11,32
 	mov r26=b5
 	;;
-	st8 [r14]=r23,16	// save b2
-	st8 [r15]=r24,16	// save b3
+	st8 [r14]=r22,SW(B4)-SW(B1)		// save b1
+	st8 [r15]=r24,SW(AR_PFS)-SW(B3)		// save b3
 	mov r21=ar.lc		// I-unit
 	stf.spill [r2]=f12,32
 	stf.spill [r3]=f13,32
 	;;
-	st8 [r14]=r25,16	// save b4
-	st8 [r15]=r26,16	// save b5
+	st8 [r14]=r25,SW(B5)-SW(B4)		// save b4
+	st8 [r15]=r16,SW(AR_LC)-SW(AR_PFS)	// save ar.pfs
 	stf.spill [r2]=f14,32
 	stf.spill [r3]=f15,32
 	;;
-	st8 [r14]=r16		// save ar.pfs
+	st8 [r14]=r26				// save b5
 	st8 [r15]=r21				// save ar.lc
 	stf.spill [r2]=f16,32
 	stf.spill [r3]=f17,32
@@ -284,26 +303,26 @@ GLOBAL_ENTRY(save_switch_stack)
 	;;
 	stf.spill [r2]=f24,32
 	stf.spill [r3]=f25,32
-	add r14=SW(CALLER_UNAT)+16,sp
 	;;
 	stf.spill [r2]=f26,32
 	stf.spill [r3]=f27,32
-	add r15=SW(AR_FPSR)+16,sp
 	;;
 	stf.spill [r2]=f28,32
 	stf.spill [r3]=f29,32
-	st8 [r14]=r17		// save caller_unat
-	st8 [r15]=r18		// save fpsr
-	mov r21=pr
 	;;
-	stf.spill [r2]=f30,(SW(AR_UNAT)-SW(F30))
-	stf.spill [r3]=f31,(SW(AR_RNAT)-SW(F31))
+	stf.spill [r2]=f30,SW(AR_UNAT)-SW(F30)
+	stf.spill [r3]=f31,SW(PR)-SW(F31)
+	add r14=SW(CALLER_UNAT)+16,sp
 	;;
-	st8 [r2]=r29,16		// save ar.unat
-	st8 [r3]=r19,16		// save ar.rnat
+	st8 [r2]=r29,SW(AR_RNAT)-SW(AR_UNAT)	// save ar.unat
+	st8 [r14]=r17,SW(AR_FPSR)-SW(CALLER_UNAT) // save caller_unat
+	mov r21=pr
 	;;
-	st8 [r2]=r20		// save ar.bspstore
+	st8 [r2]=r19,SW(AR_BSPSTORE)-SW(AR_RNAT) // save ar.rnat
 	st8 [r3]=r21				// save predicate registers
+	;;
+	st8 [r2]=r20				// save ar.bspstore
+	st8 [r14]=r18				// save fpsr
 	mov ar.rsc=3		// put RSE back into eager mode, pl 0
 	br.cond.sptk.many b7
 END(save_switch_stack)
@@ -647,23 +666,38 @@ dont_preserve_current_frame:
 	/*
 	 * To prevent leaking bits between the kernel and user-space,
 	 * we must clear the stacked registers in the "invalid" partition here.
-	 * Not pretty, but at least it's fast (3.34 registers/cycle).
-	 * Architecturally, this loop could go at 4.67 registers/cycle, but that would
-	 * oversubscribe Itanium.
+	 * Not pretty, but at least it's fast (3.34 registers/cycle on Itanium,
+	 * 5 registers/cycle on McKinley).
 	 */
 #	define pRecurse	p6
 #	define pReturn	p7
+#ifdef CONFIG_ITANIUM
 #	define Nregs	10
+#else
+#	define Nregs	14
+#endif
 	alloc loc0=ar.pfs,2,Nregs-2,2,0
 	shr.u loc1=r18,9		// RNaTslots <= dirtySize / (64*8) + 1
 	sub r17=r17,r18			// r17 = (physStackedSize + 8) - dirtySize
 	;;
+#if 1
+	.align 32		// see comment below about gas bug...
+#endif
 	mov ar.rsc=r19			// load ar.rsc to be used for "loadrs"
 	shladd in0=loc1,3,r17
 	mov in1=0
+#if 0
+	// gas-2.12.90 is unable to generate a stop bit after .align, which is bad,
+	// because alloc must be at the beginning of an insn-group.
+	.align 32
+#else
+	nop 0
+	nop 0
+	nop 0
+#endif
 	;;
-//	.align 32	// gas-2.11.90 is unable to generate a stop bit after .align
 rse_clear_invalid:
+#ifdef CONFIG_ITANIUM
 	// cycle 0
  { .mii
 	alloc loc0=ar.pfs,2,Nregs-2,2,0
@@ -692,9 +726,31 @@ rse_clear_invalid:
 	mov loc7=0
 (pReturn) br.ret.sptk.many b6
 }
+#else /* !CONFIG_ITANIUM */
+	alloc loc0=ar.pfs,2,Nregs-2,2,0
+	cmp.lt pRecurse,p0=Nregs*8,in0	// if more than Nregs regs left to clear, (re)curse
+	add out0=-Nregs*8,in0
+	add out1=1,in1			// increment recursion count
+	mov loc1=0
+	mov loc2=0
+	;;
+	mov loc3=0
+	mov loc4=0
+	mov loc9=0
+	mov loc5=0
+	mov loc6=0
+(pRecurse) br.call.sptk.many b6=rse_clear_invalid
+	;;
+	mov loc7=0
+	mov loc8=0
+	cmp.ne pReturn,p0=r0,in1	// if recursion count != 0, we need to do a br.ret
+	mov loc10=0
+	mov loc11=0
+(pReturn) br.ret.sptk.many b6
+#endif /* !CONFIG_ITANIUM */
 #	undef pRecurse
 #	undef pReturn
-
+	;;
 	alloc r17=ar.pfs,0,0,0,0	// drop current register frame
 	;;
 	loadrs
@@ -1087,7 +1143,11 @@ sys_call_table:
 	data8 sys_sched_get_priority_min
 	data8 sys_sched_rr_get_interval
 	data8 sys_nanosleep
+#if defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE)
 	data8 sys_nfsservctl
+#else
+	data8 sys_ni_syscall
+#endif
 	data8 sys_prctl				// 1170
 	data8 sys_getpagesize
 	data8 sys_mmap2
@@ -1147,14 +1207,10 @@ sys_call_table:
 	data8 sys_removexattr
 	data8 sys_lremovexattr
 	data8 sys_fremovexattr
-#if 0
 	data8 sys_tkill
-#else
-	data8 ia64_ni_syscall
-#endif
-	data8 ia64_ni_syscall			// 1230
-	data8 ia64_ni_syscall
-	data8 ia64_ni_syscall
+	data8 sys_futex				// 1230
+	data8 sys_sched_setaffinity
+	data8 sys_sched_getaffinity
 	data8 ia64_ni_syscall
 	data8 ia64_ni_syscall
 	data8 ia64_ni_syscall			// 1235

arch/ia64/kernel/head.S

@@ -560,137 +560,114 @@ GLOBAL_ENTRY(__ia64_load_fpu)
 END(__ia64_load_fpu)
 
 GLOBAL_ENTRY(__ia64_init_fpu)
-	alloc r2=ar.pfs,0,0,0,0
-	stf.spill [sp]=f0
-	mov      f32=f0
-	;;
-	ldf.fill f33=[sp]
-	ldf.fill f34=[sp]
-	mov      f35=f0
-	;;
-	ldf.fill f36=[sp]
-	ldf.fill f37=[sp]
-	mov      f38=f0
-	;;
-	ldf.fill f39=[sp]
-	ldf.fill f40=[sp]
-	mov      f41=f0
-	;;
-	ldf.fill f42=[sp]
-	ldf.fill f43=[sp]
-	mov      f44=f0
-	;;
-	ldf.fill f45=[sp]
-	ldf.fill f46=[sp]
-	mov      f47=f0
-	;;
-	ldf.fill f48=[sp]
-	ldf.fill f49=[sp]
-	mov      f50=f0
-	;;
-	ldf.fill f51=[sp]
-	ldf.fill f52=[sp]
-	mov      f53=f0
-	;;
-	ldf.fill f54=[sp]
-	ldf.fill f55=[sp]
-	mov      f56=f0
-	;;
-	ldf.fill f57=[sp]
-	ldf.fill f58=[sp]
-	mov      f59=f0
-	;;
-	ldf.fill f60=[sp]
-	ldf.fill f61=[sp]
-	mov      f62=f0
-	;;
-	ldf.fill f63=[sp]
-	ldf.fill f64=[sp]
-	mov      f65=f0
-	;;
-	ldf.fill f66=[sp]
-	ldf.fill f67=[sp]
-	mov      f68=f0
-	;;
-	ldf.fill f69=[sp]
-	ldf.fill f70=[sp]
-	mov      f71=f0
-	;;
-	ldf.fill f72=[sp]
-	ldf.fill f73=[sp]
-	mov      f74=f0
-	;;
-	ldf.fill f75=[sp]
-	ldf.fill f76=[sp]
-	mov      f77=f0
-	;;
-	ldf.fill f78=[sp]
-	ldf.fill f79=[sp]
-	mov      f80=f0
-	;;
-	ldf.fill f81=[sp]
-	ldf.fill f82=[sp]
-	mov      f83=f0
-	;;
-	ldf.fill f84=[sp]
-	ldf.fill f85=[sp]
-	mov      f86=f0
-	;;
-	ldf.fill f87=[sp]
-	ldf.fill f88=[sp]
-	mov      f89=f0
-	;;
-	ldf.fill f90=[sp]
-	ldf.fill f91=[sp]
-	mov      f92=f0
-	;;
-	ldf.fill f93=[sp]
-	ldf.fill f94=[sp]
-	mov      f95=f0
-	;;
-	ldf.fill f96=[sp]
-	ldf.fill f97=[sp]
-	mov      f98=f0
-	;;
-	ldf.fill f99=[sp]
-	ldf.fill f100=[sp]
-	mov      f101=f0
-	;;
-	ldf.fill f102=[sp]
-	ldf.fill f103=[sp]
-	mov      f104=f0
-	;;
-	ldf.fill f105=[sp]
-	ldf.fill f106=[sp]
-	mov      f107=f0
-	;;
-	ldf.fill f108=[sp]
-	ldf.fill f109=[sp]
-	mov      f110=f0
-	;;
-	ldf.fill f111=[sp]
-	ldf.fill f112=[sp]
-	mov      f113=f0
-	;;
-	ldf.fill f114=[sp]
-	ldf.fill f115=[sp]
-	mov      f116=f0
-	;;
-	ldf.fill f117=[sp]
-	ldf.fill f118=[sp]
-	mov      f119=f0
-	;;
-	ldf.fill f120=[sp]
-	ldf.fill f121=[sp]
-	mov      f122=f0
-	;;
-	ldf.fill f123=[sp]
-	ldf.fill f124=[sp]
-	mov      f125=f0
+	stf.spill [sp]=f0		// M3
+	mov	 f32=f0			// F
+	nop.b	 0
+
+	ldfps	 f33,f34=[sp]		// M0
+	ldfps	 f35,f36=[sp]		// M1
+	mov      f37=f0			// F
 	;;
-	ldf.fill f126=[sp]
-	mov      f127=f0
-	br.ret.sptk.many rp
+
+	setf.s	 f38=r0			// M2
+	setf.s	 f39=r0			// M3
+	mov      f40=f0			// F
+
+	ldfps	 f41,f42=[sp]		// M0
+	ldfps	 f43,f44=[sp]		// M1
+	mov      f45=f0			// F
+
+	setf.s	 f46=r0			// M2
+	setf.s	 f47=r0			// M3
+	mov      f48=f0			// F
+
+	ldfps	 f49,f50=[sp]		// M0
+	ldfps	 f51,f52=[sp]		// M1
+	mov      f53=f0			// F
+
+	setf.s	 f54=r0			// M2
+	setf.s	 f55=r0			// M3
+	mov      f56=f0			// F
+
+	ldfps	 f57,f58=[sp]		// M0
+	ldfps	 f59,f60=[sp]		// M1
+	mov      f61=f0			// F
+
+	setf.s	 f62=r0			// M2
+	setf.s	 f63=r0			// M3
+	mov      f64=f0			// F
+
+	ldfps	 f65,f66=[sp]		// M0
+	ldfps	 f67,f68=[sp]		// M1
+	mov      f69=f0			// F
+
+	setf.s	 f70=r0			// M2
+	setf.s	 f71=r0			// M3
+	mov      f72=f0			// F
+
+	ldfps	 f73,f74=[sp]		// M0
+	ldfps	 f75,f76=[sp]		// M1
+	mov      f77=f0			// F
+
+	setf.s	 f78=r0			// M2
+	setf.s	 f79=r0			// M3
+	mov      f80=f0			// F
+
+	ldfps	 f81,f82=[sp]		// M0
+	ldfps	 f83,f84=[sp]		// M1
+	mov      f85=f0			// F
+
+	setf.s	 f86=r0			// M2
+	setf.s	 f87=r0			// M3
+	mov      f88=f0			// F
+
+	/*
+	 * When the instructions are cached, it would be faster to initialize
+	 * the remaining registers with simply mov instructions (F-unit).
+	 * This gets the time down to ~29 cycles.  However, this would use up
+	 * 33 bundles, whereas continuing with the above pattern yields
+	 * 10 bundles and ~30 cycles.
+	 */
+
+	ldfps	 f89,f90=[sp]		// M0
+	ldfps	 f91,f92=[sp]		// M1
+	mov      f93=f0			// F
+
+	setf.s	 f94=r0			// M2
+	setf.s	 f95=r0			// M3
+	mov      f96=f0			// F
+
+	ldfps	 f97,f98=[sp]		// M0
+	ldfps	 f99,f100=[sp]		// M1
+	mov      f101=f0		// F
+
+	setf.s	 f102=r0		// M2
+	setf.s	 f103=r0		// M3
+	mov      f104=f0		// F
+
+	ldfps	 f105,f106=[sp]		// M0
+	ldfps	 f107,f108=[sp]		// M1
+	mov      f109=f0		// F
+
+	setf.s	 f110=r0		// M2
+	setf.s	 f111=r0		// M3
+	mov      f112=f0		// F
+
+	ldfps	 f113,f114=[sp]		// M0
+	ldfps	 f115,f116=[sp]		// M1
+	mov      f117=f0		// F
+
+	setf.s	 f118=r0		// M2
+	setf.s	 f119=r0		// M3
+	mov      f120=f0		// F
+
+	ldfps	 f121,f122=[sp]		// M0
+	ldfps	 f123,f124=[sp]		// M1
+	mov      f125=f0		// F
+
+	setf.s	 f126=r0		// M2
+	setf.s	 f127=r0		// M3
+	br.ret.sptk.many rp		// F
 END(__ia64_init_fpu)
 
 /*

arch/ia64/kernel/ia64_ksyms.c

@@ -6,7 +6,11 @@
 #include <linux/module.h>
 
 #include <linux/string.h>
-EXPORT_SYMBOL_NOVERS(memset);
+#undef memset
+extern void *memset (void *, int, size_t);
+EXPORT_SYMBOL_NOVERS(memset);			/* gcc generates direct calls to memset()... */
+EXPORT_SYMBOL_NOVERS(__memset_generic);
+EXPORT_SYMBOL_NOVERS(__bzero);
 EXPORT_SYMBOL(memchr);
 EXPORT_SYMBOL(memcmp);
 EXPORT_SYMBOL_NOVERS(memcpy);
@@ -67,7 +71,7 @@ EXPORT_SYMBOL(kernel_thread);
 EXPORT_SYMBOL(last_cli_ip);
 #endif
 
-#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
 
 EXPORT_SYMBOL(flush_tlb_range);
 
@@ -147,3 +151,10 @@ EXPORT_SYMBOL(efi);
 #include <linux/proc_fs.h>
 extern struct proc_dir_entry *efi_dir;
 EXPORT_SYMBOL(efi_dir);
+
+#include <asm/machvec.h>
+#ifdef CONFIG_IA64_GENERIC
+EXPORT_SYMBOL(ia64_mv);
+#endif
+EXPORT_SYMBOL(machvec_noop);
+

arch/ia64/kernel/iosapic.c

@@ -22,6 +22,7 @@
  * 02/01/07     E. Focht        <efocht@ess.nec.de> Redirectable interrupt vectors in
  *                              iosapic_set_affinity(), initializations for
  *                              /proc/irq/#/smp_affinity
+ * 02/04/02	P. Diefenbaugh	Cleaned up ACPI PCI IRQ routing.
  */
 /*
  * Here is what the interrupt logic between a PCI device and the CPU looks like:
@@ -56,9 +57,8 @@
 #include <linux/smp_lock.h>
 #include <linux/string.h>
 #include <linux/irq.h>
+#include <linux/acpi.h>
 
-#include <asm/acpi-ext.h>
-#include <asm/acpikcfg.h>
 #include <asm/delay.h>
 #include <asm/hw_irq.h>
 #include <asm/io.h>
@@ -92,11 +92,37 @@ static struct iosapic_irq {
 	unsigned char trigger	: 1;	/* trigger mode (see iosapic.h) */
 } iosapic_irq[IA64_NUM_VECTORS];
 
+static struct iosapic {
+	char *addr;			/* base address of IOSAPIC */
+	unsigned char	pcat_compat;	/* 8259 compatibility flag */
+	unsigned char 	base_irq;	/* first irq assigned to this IOSAPIC */
+	unsigned short 	max_pin;	/* max input pin supported in this IOSAPIC */
+} iosapic_lists[256] __initdata;
+
+static int num_iosapic = 0;
+
+
+/*
+ * Find an IOSAPIC associated with an IRQ
+ */
+static inline int __init
+find_iosapic (unsigned int irq)
+{
+	int i;
+
+	for (i = 0; i < num_iosapic; i++) {
+		if ((irq - iosapic_lists[i].base_irq) < iosapic_lists[i].max_pin)
+			return i;
+	}
+
+	return -1;
+}
+
 /*
  * Translate IOSAPIC irq number to the corresponding IA-64 interrupt vector.  If no
  * entry exists, return -1.
  */
-int
+static int
 iosapic_irq_to_vector (int irq)
 {
 	int vector;
@@ -479,7 +505,7 @@ iosapic_register_platform_irq (u32 int_type, u32 global_vector,
 	int vector;
 
 	switch (int_type) {
-	case ACPI20_ENTRY_PIS_PMI:
+	      case ACPI_INTERRUPT_PMI:
 		vector = iosapic_vector;
 		/*
 		 * since PMI vector is alloc'd by FW(ACPI) not by kernel,
@@ -488,14 +514,14 @@ iosapic_register_platform_irq (u32 int_type, u32 global_vector,
 		iosapic_reassign_vector(vector);
 		delivery = IOSAPIC_PMI;
 		break;
-	case ACPI20_ENTRY_PIS_CPEI:
-		vector = IA64_PCE_VECTOR;
-		delivery = IOSAPIC_LOWEST_PRIORITY;
-		break;
-	case ACPI20_ENTRY_PIS_INIT:
+	      case ACPI_INTERRUPT_INIT:
 		vector = ia64_alloc_irq();
 		delivery = IOSAPIC_INIT;
 		break;
+	      case ACPI_INTERRUPT_CPEI:
+		vector = IA64_PCE_VECTOR;
+		delivery = IOSAPIC_LOWEST_PRIORITY;
+		break;
 	      default:
 		printk("iosapic_register_platform_irq(): invalid int type\n");
 		return -1;
@@ -542,31 +568,41 @@ iosapic_register_legacy_irq (unsigned long irq,
 void __init
 iosapic_init (unsigned long phys_addr, unsigned int base_irq, int pcat_compat)
 {
-	int i, irq, max_pin, vector, pin;
+	int irq, max_pin, vector, pin;
 	unsigned int ver;
 	char *addr;
 	static int first_time = 1;
 
 	if (first_time) {
 		first_time = 0;
-
 		for (vector = 0; vector < IA64_NUM_VECTORS; ++vector)
 			iosapic_irq[vector].pin = -1;	/* mark as unused */
+	}
 
+	if (pcat_compat) {
 		/*
-		 * Fetch the PCI interrupt routing table:
+		 * Disable the compatibility mode interrupts (8259 style), needs IN/OUT support
+		 * enabled.
 		 */
-		acpi_cf_get_pci_vectors(&pci_irq.route, &pci_irq.num_routes);
+		printk("%s: Disabling PC-AT compatible 8259 interrupts\n", __FUNCTION__);
+		outb(0xff, 0xA1);
+		outb(0xff, 0x21);
 	}
 
 	addr = ioremap(phys_addr, 0);
 	ver = iosapic_version(addr);
 	max_pin = (ver >> 16) & 0xff;
 
+	iosapic_lists[num_iosapic].addr = addr;
+	iosapic_lists[num_iosapic].pcat_compat = pcat_compat;
+	iosapic_lists[num_iosapic].base_irq = base_irq;
+	iosapic_lists[num_iosapic].max_pin = max_pin;
+	num_iosapic++;
+
 	printk("IOSAPIC: version %x.%x, address 0x%lx, IRQs 0x%02x-0x%02x\n",
 	       (ver & 0xf0) >> 4, (ver & 0x0f), phys_addr, base_irq, base_irq + max_pin);
 
-	if ((base_irq == 0) && pcat_compat)
+	if ((base_irq == 0) && pcat_compat) {
 		/*
 		 * Map the legacy ISA devices into the IOSAPIC data.  Some of these may
 		 * get reprogrammed later on with data from the ACPI Interrupt Source
@@ -590,11 +626,37 @@ iosapic_init (unsigned long phys_addr, unsigned int base_irq, int pcat_compat)
 			/* program the IOSAPIC routing table: */
 			set_rte(vector, (ia64_get_lid() >> 16) & 0xffff);
 		}
+	}
+}
+
+void __init
+iosapic_init_pci_irq (void)
+{
+	int i, index, vector, pin;
+	int base_irq, max_pin, pcat_compat;
+	unsigned int irq;
+	char *addr;
+
+	if (0 != acpi_get_prt(&pci_irq.route, &pci_irq.num_routes))
+		return;
 
 	for (i = 0; i < pci_irq.num_routes; i++) {
+
 		irq = pci_irq.route[i].irq;
 
-		if ((irq < (int)base_irq) || (irq > (int)(base_irq + max_pin)))
+		index = find_iosapic(irq);
+		if (index < 0) {
+			printk("PCI: IRQ %u has no IOSAPIC mapping\n", irq);
+			continue;
+		}
+
+		addr = iosapic_lists[index].addr;
+		base_irq = iosapic_lists[index].base_irq;
+		max_pin = iosapic_lists[index].max_pin;
+		pcat_compat = iosapic_lists[index].pcat_compat;
+		pin = irq - base_irq;
+
+		if ((unsigned) pin > max_pin)
 			/* the interrupt route is for another controller... */
 			continue;
 
@@ -607,18 +669,13 @@ iosapic_init (unsigned long phys_addr, unsigned int base_irq, int pcat_compat)
 				vector = ia64_alloc_irq();
 		}
 
-		register_irq(irq, vector, irq - base_irq,
-			     /* IOSAPIC_POL_LOW, IOSAPIC_LEVEL */
-			     IOSAPIC_LOWEST_PRIORITY, 0, 0, base_irq, addr);
+		register_irq(irq, vector, pin, IOSAPIC_LOWEST_PRIORITY, 0, 0, base_irq, addr);
 
-# ifdef DEBUG_IRQ_ROUTING
+#ifdef DEBUG_IRQ_ROUTING
 		printk("PCI: (B%d,I%d,P%d) -> IOSAPIC irq 0x%02x -> vector 0x%02x\n",
 		       pci_irq.route[i].bus, pci_irq.route[i].pci_id>>16, pci_irq.route[i].pin,
 		       iosapic_irq[vector].base_irq + iosapic_irq[vector].pin, vector);
-# endif
-
-			/* program the IOSAPIC routing table: */
-			set_rte(vector, (ia64_get_lid() >> 16) & 0xffff);
+#endif
 	}
 }
 
@@ -631,6 +688,11 @@ iosapic_pci_fixup (int phase)
 	struct hw_interrupt_type *irq_type;
 	irq_desc_t *idesc;
 
+	if (phase == 0) {
+		iosapic_init_pci_irq();
+		return;
+	}
+
 	if (phase != 1)
 		return;
 
@@ -670,10 +732,10 @@ iosapic_pci_fixup (int phase)
 
 				irq_type = &irq_type_iosapic_level;
 				idesc = irq_desc(vector);
-				if (idesc->handler != irq_type){
+				if (idesc->handler != irq_type) {
 					if (idesc->handler != &no_irq_type)
-						printk("iosapic_pci_fixup: changing vector 0x%02x from "
-						       "%s to %s\n", vector,
+						printk("iosapic_pci_fixup: changing vector 0x%02x "
+						       "from %s to %s\n", vector,
 						       idesc->handler->typename,
 						       irq_type->typename);
 					idesc->handler = irq_type;

arch/ia64/kernel/irq.c

@@ -68,6 +68,23 @@
 irq_desc_t _irq_desc[NR_IRQS] __cacheline_aligned =
 	{ [0 ... NR_IRQS-1] = { IRQ_DISABLED, &no_irq_type, NULL, 0, SPIN_LOCK_UNLOCKED}};
 
+#ifdef CONFIG_IA64_GENERIC
+struct irq_desc * __ia64_irq_desc (unsigned int irq)
+{
+	return _irq_desc + irq;
+}
+
+ia64_vector __ia64_irq_to_vector (unsigned int irq)
+{
+	return (ia64_vector) irq;
+}
+
+unsigned int __ia64_local_vector_to_irq (ia64_vector vec)
+{
+	return (unsigned int) vec;
+}
+#endif
+
 static void register_irq_proc (unsigned int irq);
 
 /*

arch/ia64/kernel/ivt.S

@@ -127,7 +127,7 @@ ENTRY(vhpt_miss)
 	;;
 (p7)	dep r17=r17,r19,(PAGE_SHIFT-3),3	// put region number bits in place
 	srlz.d					// ensure "rsm psr.dt" has taken effect
-(p6)	movl r19=__pa(SWAPPER_PGD_ADDR)		// region 5 is rooted at swapper_pg_dir
+(p6)	movl r19=__pa(swapper_pg_dir)		// region 5 is rooted at swapper_pg_dir
 (p6)	shr.u r21=r21,PGDIR_SHIFT+PAGE_SHIFT
 (p7)	shr.u r21=r21,PGDIR_SHIFT+PAGE_SHIFT-3
 	;;
@@ -413,7 +413,7 @@ ENTRY(nested_dtlb_miss)
 	;;
 (p7)	dep r17=r17,r19,(PAGE_SHIFT-3),3	// put region number bits in place
 	srlz.d
-(p6)	movl r19=__pa(SWAPPER_PGD_ADDR)		// region 5 is rooted at swapper_pg_dir
+(p6)	movl r19=__pa(swapper_pg_dir)		// region 5 is rooted at swapper_pg_dir
 (p6)	shr.u r21=r21,PGDIR_SHIFT+PAGE_SHIFT
 (p7)	shr.u r21=r21,PGDIR_SHIFT+PAGE_SHIFT-3
 	;;

arch/ia64/kernel/mca.c

@@ -41,6 +41,7 @@
 #include <linux/irq.h>
 #include <linux/smp_lock.h>
 #include <linux/bootmem.h>
+#include <linux/acpi.h>
 
 #include <asm/machvec.h>
 #include <asm/page.h>
@@ -51,7 +52,6 @@
 
 #include <asm/irq.h>
 #include <asm/hw_irq.h>
-#include <asm/acpi-ext.h>
 
 #undef MCA_PRT_XTRA_DATA
 
@@ -353,7 +353,9 @@ static int
 verify_guid (efi_guid_t *test, efi_guid_t *target)
 {
 	int     rc;
+#ifdef IA64_MCA_DEBUG_INFO
 	char out[40];
+#endif
 
 	if ((rc = efi_guidcmp(*test, *target))) {
 		IA64_MCA_DEBUG(KERN_DEBUG
@@ -497,7 +499,7 @@ ia64_mca_init(void)
 	{
 		irq_desc_t *desc;
 		unsigned int irq;
-		int cpev = acpi_request_vector(ACPI20_ENTRY_PIS_CPEI);
+		int cpev = acpi_request_vector(ACPI_INTERRUPT_CPEI);
 
 		if (cpev >= 0) {
 			for (irq = 0; irq < NR_IRQS; ++irq)

arch/ia64/kernel/minstate.h

 #include <linux/config.h>
 
+#include <asm/cache.h>
+
 #include "entry.h"
 
 /*
@@ -28,18 +30,19 @@
  * on interrupts.
  */
 #define MINSTATE_START_SAVE_MIN_VIRT								\
-	dep r1=-1,r1,61,3;				/* r1 = current (virtual) */		\
 (pUser)	mov ar.rsc=0;		/* set enforced lazy mode, pl 0, little-endian, loadrs=0 */	\
+	dep r1=-1,r1,61,3;				/* r1 = current (virtual) */		\
 	;;											\
+(pUser)	mov.m rARRNAT=ar.rnat;									\
 (pUser)	addl rKRBS=IA64_RBS_OFFSET,r1;			/* compute base of RBS */		\
-(pUser)	mov rARRNAT=ar.rnat;									\
 (pKern) mov r1=sp;					/* get sp  */				\
 	;;											\
-(pUser)	addl r1=IA64_STK_OFFSET-IA64_PT_REGS_SIZE,r1;	/* compute base of memory stack */	\
+(pUser) lfetch.fault.excl.nt1 [rKRBS];								\
 (pUser)	mov rARBSPSTORE=ar.bspstore;			/* save ar.bspstore */			\
+(pUser)	addl r1=IA64_STK_OFFSET-IA64_PT_REGS_SIZE,r1;	/* compute base of memory stack */	\
 	;;											\
-(pKern) addl r1=-IA64_PT_REGS_SIZE,r1;			/* if in kernel mode, use sp (r12) */	\
 (pUser)	mov ar.bspstore=rKRBS;				/* switch to kernel RBS */		\
+(pKern) addl r1=-IA64_PT_REGS_SIZE,r1;			/* if in kernel mode, use sp (r12) */	\
 	;;											\
 (pUser)	mov r18=ar.bsp;										\
 (pUser)	mov ar.rsc=0x3;		/* set eager mode, pl 0, little-endian, loadrs=0 */		\
@@ -125,51 +128,57 @@
 	;;											  \
 	SAVE_IFS;										  \
 	MINSTATE_START_SAVE_MIN									  \
+	add r17=L1_CACHE_BYTES,r1			/* really: biggest cache-line size */	  \
 	;;											  \
-	mov r16=r1;					/* initialize first base pointer */	  \
-	adds r17=8,r1;					/* initialize second base pointer */	  \
+	st8 [r1]=rCRIPSR;	/* save cr.ipsr */						  \
+	lfetch.fault.excl.nt1 [r17],L1_CACHE_BYTES;						  \
+	add r16=16,r1;					/* initialize first base pointer */	  \
 	;;											  \
-	st8 [r16]=rCRIPSR,16;	/* save cr.ipsr */						  \
-	st8 [r17]=rCRIIP,16;	/* save cr.iip */						  \
+	lfetch.fault.excl.nt1 [r17],L1_CACHE_BYTES;						  \
+	;;											  \
+	lfetch.fault.excl.nt1 [r17];								  \
+	adds r17=8,r1;					/* initialize second base pointer */	  \
 (pKern)	mov r18=r0;		/* make sure r18 isn't NaT */					  \
 	;;											  \
+	st8 [r17]=rCRIIP,16;	/* save cr.iip */						  \
 	st8 [r16]=rCRIFS,16;	/* save cr.ifs */						  \
-	st8 [r17]=rARUNAT,16;	/* save ar.unat */						  \
 (pUser)	sub r18=r18,rKRBS;	/* r18=RSE.ndirty*8 */						  \
 	;;											  \
+	st8 [r17]=rARUNAT,16;	/* save ar.unat */						  \
 	st8 [r16]=rARPFS,16;	/* save ar.pfs */						  \
+	shl r18=r18,16;		/* compute ar.rsc to be used for "loadrs" */			  \
+	;;											  \
 	st8 [r17]=rARRSC,16;	/* save ar.rsc */						  \
-	tbit.nz p15,p0=rCRIPSR,IA64_PSR_I_BIT							  \
-	;;			/* avoid RAW on r16 & r17 */					  \
-(pKern)	adds r16=16,r16;	/* skip over ar_rnat field */					  \
-(pKern)	adds r17=16,r17;	/* skip over ar_bspstore field */				  \
 (pUser)	st8 [r16]=rARRNAT,16;	/* save ar.rnat */						  \
+(pKern)	adds r16=16,r16;	/* skip over ar_rnat field */					  \
+	;;			/* avoid RAW on r16 & r17 */					  \
 (pUser)	st8 [r17]=rARBSPSTORE,16;	/* save ar.bspstore */					  \
-	;;											  \
 	st8 [r16]=rARPR,16;	/* save predicates */						  \
-	st8 [r17]=rB6,16;	/* save b6 */							  \
-	shl r18=r18,16;		/* compute ar.rsc to be used for "loadrs" */			  \
+(pKern)	adds r17=16,r17;	/* skip over ar_bspstore field */				  \
 	;;											  \
+	st8 [r17]=rB6,16;	/* save b6 */							  \
 	st8 [r16]=r18,16;	/* save ar.rsc value for "loadrs" */				  \
-	st8.spill [r17]=rR1,16;	/* save original r1 */						  \
+	tbit.nz p15,p0=rCRIPSR,IA64_PSR_I_BIT							  \
 	;;											  \
+.mem.offset 8,0;	st8.spill [r17]=rR1,16;	/* save original r1 */				  \
 .mem.offset 0,0;	st8.spill [r16]=r2,16;							  \
+	;;											  \
 .mem.offset 8,0;	st8.spill [r17]=r3,16;							  \
+.mem.offset 0,0;	st8.spill [r16]=r12,16;							  \
 	adds r2=IA64_PT_REGS_R16_OFFSET,r1;							  \
 	;;											  \
-.mem.offset 0,0;		st8.spill [r16]=r12,16;						  \
 .mem.offset 8,0;	st8.spill [r17]=r13,16;							  \
+.mem.offset 0,0;	st8.spill [r16]=r14,16;							  \
 	cmp.eq pNonSys,pSys=r0,r0	/* initialize pSys=0, pNonSys=1 */			  \
 	;;											  \
-.mem.offset 0,0;		st8.spill [r16]=r14,16;						  \
 .mem.offset 8,0;	st8.spill [r17]=r15,16;							  \
+.mem.offset 0,0;	st8.spill [r16]=r8,16;							  \
 	dep r14=-1,r0,61,3;									  \
 	;;											  \
-.mem.offset 0,0;		st8.spill [r16]=r8,16;						  \
 .mem.offset 8,0;	st8.spill [r17]=r9,16;							  \
+.mem.offset 0,0;	st8.spill [r16]=r10,16;							  \
 	adds r12=-16,r1;	/* switch to kernel memory stack (with 16 bytes of scratch) */	  \
 	;;											  \
-.mem.offset 0,0;		st8.spill [r16]=r10,16;						  \
 .mem.offset 8,0;	st8.spill [r17]=r11,16;							  \
 	mov r13=IA64_KR(CURRENT);	/* establish `current' */				  \
 	;;											  \
@@ -190,10 +199,12 @@
  */
 #define SAVE_REST				\
 .mem.offset 0,0;	st8.spill [r2]=r16,16;	\
-.mem.offset 8,0;	st8.spill [r3]=r17,16;	\
 	;;					\
+.mem.offset 8,0;	st8.spill [r3]=r17,16;	\
 .mem.offset 0,0;	st8.spill [r2]=r18,16;	\
+	;;					\
 .mem.offset 8,0;	st8.spill [r3]=r19,16;	\
+.mem.offset 0,0;	st8.spill [r2]=r20,16;	\
 	;;					\
 	mov r16=ar.ccv;		/* M-unit */	\
 	movl r18=FPSR_DEFAULT	/* L-unit */	\
@@ -201,30 +212,29 @@
 	mov r17=ar.fpsr;	/* M-unit */	\
 	mov ar.fpsr=r18;	/* M-unit */	\
 	;;					\
-.mem.offset 0,0;	st8.spill [r2]=r20,16;	\
 .mem.offset 8,0;	st8.spill [r3]=r21,16;	\
+.mem.offset 0,0;	st8.spill [r2]=r22,16;	\
 	mov r18=b0;				\
 	;;					\
-.mem.offset 0,0;	st8.spill [r2]=r22,16;	\
 .mem.offset 8,0;	st8.spill [r3]=r23,16;	\
+.mem.offset 0,0;	st8.spill [r2]=r24,16;	\
 	mov r19=b7;				\
 	;;					\
-.mem.offset 0,0;	st8.spill [r2]=r24,16;	\
 .mem.offset 8,0;	st8.spill [r3]=r25,16;	\
-	;;					\
 .mem.offset 0,0;	st8.spill [r2]=r26,16;	\
-.mem.offset 8,0;	st8.spill [r3]=r27,16;	\
 	;;					\
+.mem.offset 8,0;	st8.spill [r3]=r27,16;	\
 .mem.offset 0,0;	st8.spill [r2]=r28,16;	\
-.mem.offset 8,0;	st8.spill [r3]=r29,16;	\
 	;;					\
+.mem.offset 8,0;	st8.spill [r3]=r29,16;	\
 .mem.offset 0,0;	st8.spill [r2]=r30,16;	\
-.mem.offset 8,0;	st8.spill [r3]=r31,16;	\
 	;;					\
+.mem.offset 8,0;	st8.spill [r3]=r31,16;	\
 	st8 [r2]=r16,16;	/* ar.ccv */	\
-	st8 [r3]=r17,16;	/* ar.fpsr */	\
 	;;					\
+	st8 [r3]=r17,16;	/* ar.fpsr */	\
 	st8 [r2]=r18,16;	/* b0 */	\
+	;;					\
 	st8 [r3]=r19,16+8;	/* b7 */	\
 	;;					\
 	stf.spill [r2]=f6,32;			\

arch/ia64/kernel/pci.c

@@ -42,101 +42,183 @@
 extern void ia64_mca_check_errors( void );
 #endif
 
+struct pci_fixup pcibios_fixups[1];
+
+struct pci_ops *pci_root_ops;
+
+int (*pci_config_read)(int seg, int bus, int dev, int fn, int reg, int len, u32 *value);
+int (*pci_config_write)(int seg, int bus, int dev, int fn, int reg, int len, u32 value);
+
+
 /*
- * This interrupt-safe spinlock protects all accesses to PCI
- * configuration space.
+ * Low-level SAL-based PCI configuration access functions. Note that SAL
+ * calls are already serialized (via sal_lock), so we don't need another
+ * synchronization mechanism here.  Not using segment number (yet).
  */
-static spinlock_t pci_lock = SPIN_LOCK_UNLOCKED;
 
-struct pci_fixup pcibios_fixups[] = {
-	{ 0 }
-};
+#define PCI_SAL_ADDRESS(bus, dev, fn, reg) \
+	((u64)(bus << 16) | (u64)(dev << 11) | (u64)(fn << 8) | (u64)(reg))
 
-/* Macro to build a PCI configuration address to be passed as a parameter to SAL. */
+static int
+pci_sal_read (int seg, int bus, int dev, int fn, int reg, int len, u32 *value)
+{
+	int result = 0;
+	u64 data = 0;
 
-#define PCI_CONFIG_ADDRESS(dev, where) \
-	(((u64) dev->bus->number << 16) | ((u64) (dev->devfn & 0xff) << 8) | (where & 0xff))
+	if (!value || (bus > 255) || (dev > 31) || (fn > 7) || (reg > 255))
+		return -EINVAL;
+
+	result = ia64_sal_pci_config_read(PCI_SAL_ADDRESS(bus, dev, fn, reg), len, &data);
+
+	*value = (u32) data;
+
+	return result;
+}
 
 static int
-pci_conf_read_config_byte(struct pci_dev *dev, int where, u8 *value)
+pci_sal_write (int seg, int bus, int dev, int fn, int reg, int len, u32 value)
 {
-	s64 status;
-	u64 lval;
+	if ((bus > 255) || (dev > 31) || (fn > 7) || (reg > 255))
+		return -EINVAL;
 
-	status = ia64_sal_pci_config_read(PCI_CONFIG_ADDRESS(dev, where), 1, &lval);
-	*value = lval;
-	return status;
+	return ia64_sal_pci_config_write(PCI_SAL_ADDRESS(bus, dev, fn, reg), len, value);
+}
+
+
+static int
+pci_sal_read_config_byte (struct pci_dev *dev, int where, u8 *value)
+{
+	int result = 0;
+	u32 data = 0;
+
+	if (!value)
+		return -EINVAL;
+
+	result = pci_sal_read(0, dev->bus->number, PCI_SLOT(dev->devfn),
+			      PCI_FUNC(dev->devfn), where, 1, &data);
+
+	*value = (u8) data;
+
+	return result;
 }
 
 static int
-pci_conf_read_config_word(struct pci_dev *dev, int where, u16 *value)
+pci_sal_read_config_word (struct pci_dev *dev, int where, u16 *value)
 {
-	s64 status;
-	u64 lval;
+	int result = 0;
+	u32 data = 0;
+
+	if (!value)
+		return -EINVAL;
 
-	status = ia64_sal_pci_config_read(PCI_CONFIG_ADDRESS(dev, where), 2, &lval);
-	*value = lval;
-	return status;
+	result = pci_sal_read(0, dev->bus->number, PCI_SLOT(dev->devfn),
+			      PCI_FUNC(dev->devfn), where, 2, &data);
+
+	*value = (u16) data;
+
+	return result;
 }
 
 static int
-pci_conf_read_config_dword(struct pci_dev *dev, int where, u32 *value)
+pci_sal_read_config_dword (struct pci_dev *dev, int where, u32 *value)
 {
-	s64 status;
-	u64 lval;
+	if (!value)
+		return -EINVAL;
 
-	status = ia64_sal_pci_config_read(PCI_CONFIG_ADDRESS(dev, where), 4, &lval);
-	*value = lval;
-	return status;
+	return pci_sal_read(0, dev->bus->number, PCI_SLOT(dev->devfn),
+			    PCI_FUNC(dev->devfn), where, 4, value);
 }
 
 static int
-pci_conf_write_config_byte (struct pci_dev *dev, int where, u8 value)
+pci_sal_write_config_byte (struct pci_dev *dev, int where, u8 value)
 {
-	return ia64_sal_pci_config_write(PCI_CONFIG_ADDRESS(dev, where), 1, value);
+	return pci_sal_write(0, dev->bus->number, PCI_SLOT(dev->devfn),
+			     PCI_FUNC(dev->devfn), where, 1, value);
 }
 
 static int
-pci_conf_write_config_word (struct pci_dev *dev, int where, u16 value)
+pci_sal_write_config_word (struct pci_dev *dev, int where, u16 value)
 {
-	return ia64_sal_pci_config_write(PCI_CONFIG_ADDRESS(dev, where), 2, value);
+	return pci_sal_write(0, dev->bus->number, PCI_SLOT(dev->devfn),
+			     PCI_FUNC(dev->devfn), where, 2, value);
 }
 
 static int
-pci_conf_write_config_dword (struct pci_dev *dev, int where, u32 value)
+pci_sal_write_config_dword (struct pci_dev *dev, int where, u32 value)
 {
-	return ia64_sal_pci_config_write(PCI_CONFIG_ADDRESS(dev, where), 4, value);
+	return pci_sal_write(0, dev->bus->number, PCI_SLOT(dev->devfn),
+			     PCI_FUNC(dev->devfn), where, 4, value);
 }
 
-struct pci_ops pci_conf = {
-      pci_conf_read_config_byte,
-      pci_conf_read_config_word,
-      pci_conf_read_config_dword,
-      pci_conf_write_config_byte,
-      pci_conf_write_config_word,
-      pci_conf_write_config_dword
+struct pci_ops pci_sal_ops = {
+	pci_sal_read_config_byte,
+	pci_sal_read_config_word,
+	pci_sal_read_config_dword,
+	pci_sal_write_config_byte,
+	pci_sal_write_config_word,
+	pci_sal_write_config_dword
 };
 
+
 /*
  * Initialization. Uses the SAL interface
  */
+
+struct pci_bus *
+pcibios_scan_root(int seg, int bus)
+{
+	struct list_head *list = NULL;
+	struct pci_bus *pci_bus = NULL;
+
+	list_for_each(list, &pci_root_buses) {
+		pci_bus = pci_bus_b(list);
+		if (pci_bus->number == bus) {
+			/* Already scanned */
+			printk("PCI: Bus (%02x:%02x) already probed\n", seg, bus);
+			return pci_bus;
+		}
+	}
+
+	printk("PCI: Probing PCI hardware on bus (%02x:%02x)\n", seg, bus);
+
+	return pci_scan_bus(bus, pci_root_ops, NULL);
+}
+
+void __init
+pcibios_config_init (void)
+{
+	if (pci_root_ops)
+		return;
+
+	printk("PCI: Using SAL to access configuration space\n");
+
+	pci_root_ops = &pci_sal_ops;
+	pci_config_read = pci_sal_read;
+	pci_config_write = pci_sal_write;
+
+	return;
+}
+
 void __init
 pcibios_init (void)
 {
 #	define PCI_BUSES_TO_SCAN 255
-	int i;
+	int i = 0;
 
 #ifdef CONFIG_IA64_MCA
 	ia64_mca_check_errors();    /* For post-failure MCA error logging */
 #endif
 
-	platform_pci_fixup(0);	/* phase 0 initialization (before PCI bus has been scanned) */
+	pcibios_config_init();
+
+	platform_pci_fixup(0);	/* phase 0 fixups (before buses scanned) */
 
 	printk("PCI: Probing PCI hardware\n");
 	for (i = 0; i < PCI_BUSES_TO_SCAN; i++)
-		pci_scan_bus(i, &pci_conf, NULL);
+		pci_scan_bus(i, pci_root_ops, NULL);
+
+	platform_pci_fixup(1);	/* phase 1 fixups (after buses scanned) */
 
-	platform_pci_fixup(1);	/* phase 1 initialization (after PCI bus has been scanned) */
 	return;
 }
 
@@ -186,7 +268,12 @@ pcibios_fixup_pbus_ranges (struct pci_bus * bus, struct pbus_set_ranges_data * r
 int
 pcibios_enable_device (struct pci_dev *dev)
 {
+	if (!dev)
+		return -EINVAL;
+
 	/* Not needed, since we enable all devices at startup.  */
+
+	printk(KERN_INFO "PCI: Found IRQ %d for device %s\n", dev->irq, dev->slot_name);
 	return 0;
 }
 
@@ -233,8 +320,7 @@ pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma,
 		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
 	if (remap_page_range(vma, vma->vm_start, vma->vm_pgoff << PAGE_SHIFT,
-			     vma->vm_end - vma->vm_start,
-			     vma->vm_page_prot))
+			     vma->vm_end - vma->vm_start, vma->vm_page_prot))
 		return -EAGAIN;
 
 	return 0;

arch/ia64/kernel/process.c

@@ -24,7 +24,7 @@
 #include <asm/efi.h>
 #include <asm/elf.h>
 #include <asm/perfmon.h>
-#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
 #include <asm/processor.h>
 #include <asm/sal.h>
 #include <asm/uaccess.h>
@@ -145,7 +145,7 @@ do_notify_resume_user (sigset_t *oldset, struct sigscratch *scr, long in_syscall
 /*
  * We use this if we don't have any better idle routine..
  */
-static void
+void
 default_idle (void)
 {
 	/* may want to do PAL_LIGHT_HALT here... */
@@ -660,7 +660,7 @@ dup_task_struct(struct task_struct *orig)
 {
 	struct task_struct *tsk;
 
-	tsk = __get_free_pages(GFP_KERNEL, KERNEL_STACK_SIZE_ORDER);
+	tsk = (void *) __get_free_pages(GFP_KERNEL, KERNEL_STACK_SIZE_ORDER);
 	if (!tsk)
 		return NULL;
 

arch/ia64/kernel/semaphore.c

 /*
  * IA-64 semaphore implementation (derived from x86 version).
  *
- * Copyright (C) 1999-2000 Hewlett-Packard Co
- * Copyright (C) 1999-2000 David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 1999-2000, 2002 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
  */
 
 /*
@@ -25,6 +25,7 @@
  */
 #include <linux/sched.h>
 
+#include <asm/errno.h>
 #include <asm/semaphore.h>
 
 /*

arch/ia64/kernel/setup.c

@@ -19,6 +19,7 @@
 #include <linux/config.h>
 #include <linux/init.h>
 
+#include <linux/acpi.h>
 #include <linux/bootmem.h>
 #include <linux/console.h>
 #include <linux/delay.h>
@@ -30,7 +31,6 @@
 #include <linux/threads.h>
 #include <linux/tty.h>
 
-#include <asm/acpi-ext.h>
 #include <asm/ia32.h>
 #include <asm/page.h>
 #include <asm/machvec.h>
@@ -54,7 +54,10 @@
 
 extern char _end;
 
+#ifdef CONFIG_SMP
 unsigned long __per_cpu_offset[NR_CPUS];
+#endif
+
 struct cpuinfo_ia64 cpu_info __per_cpu_data;
 
 unsigned long ia64_phys_stacked_size_p8;
@@ -64,6 +67,8 @@ struct screen_info screen_info;
 
 unsigned long ia64_iobase;	/* virtual address for I/O accesses */
 
+unsigned char aux_device_present = 0xaa;        /* XXX remove this when legacy I/O is gone */
+
 #define COMMAND_LINE_SIZE	512
 
 char saved_command_line[COMMAND_LINE_SIZE]; /* used in proc filesystem */
@@ -282,6 +287,7 @@ void __init
 setup_arch (char **cmdline_p)
 {
 	extern unsigned long ia64_iobase;
+	unsigned long phys_iobase;
 
 	unw_init();
 
@@ -314,24 +320,23 @@ setup_arch (char **cmdline_p)
 #endif
 
 	/*
-	 *  Set `iobase' to the appropriate address in region 6
-	 *    (uncached access range)
+	 *  Set `iobase' to the appropriate address in region 6 (uncached access range).
 	 *
-	 *  The EFI memory map is the "prefered" location to get the I/O port
-	 *  space base, rather the relying on AR.KR0. This should become more
-	 *  clear in future SAL specs. We'll fall back to getting it out of
-	 *  AR.KR0 if no appropriate entry is found in the memory map.
+	 *  The EFI memory map is the "preferred" location to get the I/O port space base,
+	 *  rather the relying on AR.KR0. This should become more clear in future SAL
+	 *  specs. We'll fall back to getting it out of AR.KR0 if no appropriate entry is
+	 *  found in the memory map.
 	 */
-	ia64_iobase = efi_get_iobase();
-	if (ia64_iobase)
+	phys_iobase = efi_get_iobase();
+	if (phys_iobase)
 		/* set AR.KR0 since this is all we use it for anyway */
-		ia64_set_kr(IA64_KR_IO_BASE, ia64_iobase);
+		ia64_set_kr(IA64_KR_IO_BASE, phys_iobase);
 	else {
-		ia64_iobase = ia64_get_kr(IA64_KR_IO_BASE);
+		phys_iobase = ia64_get_kr(IA64_KR_IO_BASE);
 		printk("No I/O port range found in EFI memory map, falling back to AR.KR0\n");
-		printk("I/O port base = 0x%lx\n", ia64_iobase);
+		printk("I/O port base = 0x%lx\n", phys_iobase);
 	}
-	ia64_iobase = __IA64_UNCACHED_OFFSET | (ia64_iobase & ~PAGE_OFFSET);
+	ia64_iobase = (unsigned long) ioremap(phys_iobase, 0);
 
 #ifdef CONFIG_SMP
 	cpu_physical_id(0) = hard_smp_processor_id();
@@ -339,19 +344,22 @@ setup_arch (char **cmdline_p)
 
 	cpu_init();	/* initialize the bootstrap CPU */
 
-	if (efi.acpi20) {
-		/* Parse the ACPI 2.0 tables */
-		acpi20_parse(efi.acpi20);
-	} else if (efi.acpi) {
-		/* Parse the ACPI tables */
-		acpi_parse(efi.acpi);
-	}
-
+#ifdef CONFIG_ACPI_BOOT
+	acpi_boot_init(*cmdline_p);
+#endif
 #ifdef CONFIG_VT
+# if defined(CONFIG_DUMMY_CONSOLE)
+	conswitchp = &dummy_con;
+# endif
 # if defined(CONFIG_VGA_CONSOLE)
+	/*
+	 * Non-legacy systems may route legacy VGA MMIO range to system
+	 * memory.  vga_con probes the MMIO hole, so memory looks like
+	 * a VGA device to it.  The EFI memory map can tell us if it's
+	 * memory so we can avoid this problem.
+	 */
+	if (efi_mem_type(0xA0000) != EFI_CONVENTIONAL_MEMORY)
 		conswitchp = &vga_con;
-# elif defined(CONFIG_DUMMY_CONSOLE)
-	conswitchp = &dummy_con;
 # endif
 #endif
 
@@ -522,20 +530,25 @@ setup_per_cpu_areas (void)
 void
 cpu_init (void)
 {
-	extern char __per_cpu_start[], __phys_per_cpu_start[], __per_cpu_end[];
+	extern char __per_cpu_start[], __phys_per_cpu_start[];
 	extern void __init ia64_mmu_init (void *);
 	unsigned long num_phys_stacked;
 	pal_vm_info_2_u_t vmi;
 	unsigned int max_ctx;
 	struct cpuinfo_ia64 *my_cpu_info;
 	void *my_cpu_data;
+
+#ifdef CONFIG_SMP
+	extern char __per_cpu_end[];
 	int cpu = smp_processor_id();
 
 	my_cpu_data = alloc_bootmem_pages(__per_cpu_end - __per_cpu_start);
 	memcpy(my_cpu_data, __phys_per_cpu_start, __per_cpu_end - __per_cpu_start);
-
 	__per_cpu_offset[cpu] = (char *) my_cpu_data - __per_cpu_start;
-
+	my_cpu_info = my_cpu_data + ((char *) &cpu_info - __per_cpu_start);
+#else
+	my_cpu_data = __phys_per_cpu_start;
+#endif
 	my_cpu_info = my_cpu_data + ((char *) &cpu_info - __per_cpu_start);
 
 	/*

arch/ia64/kernel/signal.c

@@ -530,8 +530,8 @@ ia64_do_signal (sigset_t *oldset, struct sigscratch *scr, long in_syscall)
 				info.si_signo = signr;
 				info.si_errno = 0;
 				info.si_code = SI_USER;
-				info.si_pid = current->p_pptr->pid;
-				info.si_uid = current->p_pptr->uid;
+				info.si_pid = current->parent->pid;
+				info.si_uid = current->parent->uid;
 			}
 
 			/* If the (new) signal is now blocked, requeue it.  */
@@ -570,7 +570,7 @@ ia64_do_signal (sigset_t *oldset, struct sigscratch *scr, long in_syscall)
 			      case SIGSTOP:
 				current->state = TASK_STOPPED;
 				current->exit_code = signr;
-				sig = current->p_pptr->sig;
+				sig = current->parent->sig;
 				if (sig && !(sig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP))
 					notify_parent(current, SIGCHLD);
 				schedule();

arch/ia64/kernel/smp.c

@@ -48,6 +48,7 @@
 #include <asm/ptrace.h>
 #include <asm/sal.h>
 #include <asm/system.h>
+#include <asm/tlbflush.h>
 #include <asm/unistd.h>
 #include <asm/mca.h>
 
@@ -236,7 +237,7 @@ smp_call_function_single (int cpuid, void (*func) (void *info), void *info, int
 	int cpus = 1;
 
 	if (cpuid == smp_processor_id()) {
-		printk(__FUNCTION__" trying to call self\n");
+		printk("%s: trying to call self\n", __FUNCTION__);
 		return -EBUSY;
 	}
 

arch/ia64/kernel/smpboot.c

@@ -68,6 +68,7 @@ static volatile unsigned long go[SLAVE + 1];
 
 extern void __init calibrate_delay(void);
 extern void start_ap(void);
+extern unsigned long ia64_iobase;
 
 int cpucount;
 task_t *task_for_booting_cpu;
@@ -345,6 +346,11 @@ smp_callin (void)
 	 */
 	ia64_init_itm();
 
+	/*
+	 * Set I/O port base per CPU
+	 */
+	ia64_set_kr(IA64_KR_IO_BASE, __pa(ia64_iobase));
+
 #ifdef CONFIG_IA64_MCA
 	ia64_mca_cmc_vector_setup();	/* Setup vector on AP & enable */
 	ia64_mca_check_errors();	/* For post-failure MCA error logging */

arch/ia64/kernel/sys_ia64.c

@@ -47,7 +47,7 @@ arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len
 		/* At this point:  (!vmm || addr < vmm->vm_end). */
 		if (TASK_SIZE - len < addr)
 			return -ENOMEM;
-		if (rgn_offset(addr) + len > RGN_MAP_LIMIT)	/* no risk of overflow here... */
+		if (REGION_OFFSET(addr) + len > RGN_MAP_LIMIT)	/* no risk of overflow here... */
 			return -ENOMEM;
 		if (!vmm || addr + len <= vmm->vm_start)
 			return addr;
@@ -126,7 +126,7 @@ ia64_brk (unsigned long brk, long arg1, long arg2, long arg3,
 	}
 
 	/* Check against unimplemented/unmapped addresses: */
-	if ((newbrk - oldbrk) > RGN_MAP_LIMIT || rgn_offset(newbrk) > RGN_MAP_LIMIT)
+	if ((newbrk - oldbrk) > RGN_MAP_LIMIT || REGION_OFFSET(newbrk) > RGN_MAP_LIMIT)
 		goto out;
 
 	/* Check against rlimit.. */
@@ -206,7 +206,7 @@ do_mmap2 (unsigned long addr, unsigned long len, int prot, int flags, int fd, un
 	 * or across a region boundary.  Note: RGN_MAP_LIMIT is equal to 2^n-PAGE_SIZE
 	 * (for some integer n <= 61) and len > 0.
 	 */
-	roff = rgn_offset(addr);
+	roff = REGION_OFFSET(addr);
 	if ((len > RGN_MAP_LIMIT) || (roff > (RGN_MAP_LIMIT - len))) {
 		addr = -EINVAL;
 		goto out;

arch/ia64/kernel/traps.c

@@ -214,7 +214,8 @@ ia64_ni_syscall (unsigned long arg0, unsigned long arg1, unsigned long arg2, uns
 {
 	struct pt_regs *regs = (struct pt_regs *) &stack;
 
-	printk("<sc%ld(%lx,%lx,%lx,%lx)>\n", regs->r15, arg0, arg1, arg2, arg3);
+	printk("%s(%d): <sc%ld(%lx,%lx,%lx,%lx)>\n", current->comm, current->pid,
+	       regs->r15, arg0, arg1, arg2, arg3);
 	return -ENOSYS;
 }
 

arch/ia64/kernel/unwind_i.h

@@ -103,7 +103,7 @@ struct unw_state_record {
 	unsigned int in_body : 1;	/* are we inside a body (as opposed to a prologue)? */
 	unsigned long flags;		/* see UNW_FLAG_* in unwind.h */
 
-	u8 *imask;			/* imask of of spill_mask record or NULL */
+	u8 *imask;			/* imask of spill_mask record or NULL */
 	unsigned long pr_val;		/* predicate values */
 	unsigned long pr_mask;		/* predicate mask */
 	long spill_offset;		/* psp-relative offset for spill base */

arch/ia64/lib/Makefile

@@ -16,6 +16,9 @@ obj-y := __divsi3.o __udivsi3.o __modsi3.o __umodsi3.o					\
 	flush.o io.o do_csum.o								\
 	memcpy.o memset.o strlen.o swiotlb.o
 
+obj-$(CONFIG_ITANIUM) += copy_page.o
+obj-$(CONFIG_MCKINLEY) += copy_page_mck.o
+
 IGNORE_FLAGS_OBJS =	__divsi3.o __udivsi3.o __modsi3.o __umodsi3.o \
 			__divdi3.o __udivdi3.o __moddi3.o __umoddi3.o
 

arch/ia64/lib/copy_page_mck.S

+/*
+ * McKinley-optimized version of copy_page().
+ *
+ * Copyright (C) 2002 Hewlett-Packard Co
+ *	David Mosberger <davidm@hpl.hp.com>
+ *
+ * Inputs:
+ *	in0:	address of target page
+ *	in1:	address of source page
+ * Output:
+ *	no return value
+ *
+ * General idea:
+ *	- use regular loads and stores to prefetch data to avoid consuming M-slot just for
+ *	  lfetches => good for in-cache performance
+ *	- avoid l2 bank-conflicts by not storing into the same 16-byte bank within a single
+ *	  cycle
+ *
+ * Principle of operation:
+ *	First, note that L1 has a line-size of 64 bytes and L2 a line-size of 128 bytes.
+ *	To avoid secondary misses in L2, we prefetch both source and destination with a line-size
+ *	of 128 bytes.  When both of these lines are in the L2 and the first half of the
+ *	source line is in L1, we start copying the remaining words.  The second half of the
+ *	source line is prefetched in an earlier iteration, so that by the time we start
+ *	accessing it, it's also present in the L1.
+ *
+ *	We use a software-pipelined loop to control the overall operation.  The pipeline
+ *	has 2*PREFETCH_DIST+K stages.  The first PREFETCH_DIST stages are used for prefetching
+ *	source cache-lines.  The second PREFETCH_DIST stages are used for prefetching destination
+ *	cache-lines, the last K stages are used to copy the cache-line words not copied by
+ *	the prefetches.  The four relevant points in the pipelined are called A, B, C, D:
+ *	p[A] is TRUE if a source-line should be prefetched, p[B] is TRUE if a destination-line
+ *	should be prefetched, p[C] is TRUE if the second half of an L2 line should be brought
+ *	into L1D and p[D] is TRUE if a cacheline needs to be copied.
+ *
+ *	This all sounds very complicated, but thanks to the modulo-scheduled loop support,
+ *	the resulting code is very regular and quite easy to follow (once you get the idea).
+ *
+ *	As a secondary optimization, the first 2*PREFETCH_DIST iterations are implemented
+ *	as the separate .prefetch_loop.  Logically, this loop performs exactly like the
+ *	main-loop (.line_copy), but has all known-to-be-predicated-off instructions removed,
+ *	so that each loop iteration is faster (again, good for cached case).
+ *
+ *	When reading the code, it helps to keep the following picture in mind:
+ *
+ *	       word 0 word 1
+ *            +------+------+---
+ *	      |	v[x] | 	t1  | ^
+ *	      |	t2   |	t3  | |
+ *	      |	t4   |	t5  | |
+ *	      |	t6   |	t7  | | 128 bytes
+ *     	      |	n[y] | 	t9  | |	(L2 cache line)
+ *	      |	t10  | 	t11 | |
+ *	      |	t12  | 	t13 | |
+ *	      |	t14  | 	t15 | v
+ *	      +------+------+---
+ *
+ *	Here, v[x] is copied by the (memory) prefetch.  n[y] is loaded at p[C]
+ *	to fetch the second-half of the L2 cache line into L1, and the tX words are copied in
+ *	an order that avoids bank conflicts.
+ */
+#include <asm/asmmacro.h>
+#include <asm/page.h>
+
+#define PREFETCH_DIST	8		// McKinley sustains 16 outstanding L2 misses (8 ld, 8 st)
+
+#define src0		r2
+#define src1		r3
+#define dst0		r9
+#define dst1		r10
+#define src_pre_mem	r11
+#define dst_pre_mem	r14
+#define src_pre_l2	r15
+#define dst_pre_l2	r16
+#define t1		r17
+#define t2		r18
+#define t3		r19
+#define t4		r20
+#define t5		t1	// alias!
+#define t6		t2	// alias!
+#define t7		t3	// alias!
+#define t9		t5	// alias!
+#define t10		t4	// alias!
+#define t11		t7	// alias!
+#define t12		t6	// alias!
+#define t14		t10	// alias!
+#define t13		r21
+#define t15		r22
+
+#define saved_lc	r23
+#define saved_pr	r24
+
+#define	A	0
+#define B	(PREFETCH_DIST)
+#define C	(B + PREFETCH_DIST)
+#define D	(C + 3)
+#define N	(D + 1)
+#define Nrot	((N + 7) & ~7)
+
+GLOBAL_ENTRY(copy_page)
+	.prologue
+	alloc r8 = ar.pfs, 2, Nrot-2, 0, Nrot
+
+	.rotr v[2*PREFETCH_DIST], n[D-C+1]
+	.rotp p[N]
+
+	.save ar.lc, saved_lc
+	mov saved_lc = ar.lc
+	.save pr, saved_pr
+	mov saved_pr = pr
+	.body
+
+	mov src_pre_mem = in1
+	mov pr.rot = 0x10000
+	mov ar.ec = 1				// special unrolled loop
+
+	mov dst_pre_mem = in0
+	mov ar.lc = 2*PREFETCH_DIST - 1
+
+	add src_pre_l2 = 8*8, in1
+	add dst_pre_l2 = 8*8, in0
+	add src0 = 8, in1			// first t1 src
+	add src1 = 3*8, in1			// first t3 src
+	add dst0 = 8, in0			// first t1 dst
+	add dst1 = 3*8, in0			// first t3 dst
+	mov t1 = (PAGE_SIZE/128) - (2*PREFETCH_DIST) - 1
+	nop.m 0
+	nop.i 0
+	;;
+	// same as .line_copy loop, but with all predicated-off instructions removed:
+.prefetch_loop:
+(p[A])	ld8 v[A] = [src_pre_mem], 128		// M0
+(p[B])	st8 [dst_pre_mem] = v[B], 128		// M2
+	br.ctop.sptk .prefetch_loop
+	;;
+	cmp.eq p16, p0 = r0, r0			// reset p16 to 1 (br.ctop cleared it to zero)
+	mov ar.lc = t1				// with 64KB pages, t1 is too big to fit in 8 bits!
+	mov ar.ec = N				// # of stages in pipeline
+	;;
+.line_copy:
+(p[D])	ld8 t2 = [src0], 3*8			// M0
+(p[D])	ld8 t4 = [src1], 3*8			// M1
+(p[B])	st8 [dst_pre_mem] = v[B], 128		// M2 prefetch dst from memory
+(p[D])	st8 [dst_pre_l2] = n[D-C], 128		// M3 prefetch dst from L2
+	;;
+(p[A])	ld8 v[A] = [src_pre_mem], 128		// M0 prefetch src from memory
+(p[C])	ld8 n[0] = [src_pre_l2], 128		// M1 prefetch src from L2
+(p[D])	st8 [dst0] =  t1, 8			// M2
+(p[D])	st8 [dst1] =  t3, 8			// M3
+	;;
+(p[D])	ld8  t5 = [src0], 8
+(p[D])	ld8  t7 = [src1], 3*8
+(p[D])	st8 [dst0] =  t2, 3*8
+(p[D])	st8 [dst1] =  t4, 3*8
+	;;
+(p[D])	ld8  t6 = [src0], 3*8
+(p[D])	ld8 t10 = [src1], 8
+(p[D])	st8 [dst0] =  t5, 8
+(p[D])	st8 [dst1] =  t7, 3*8
+	;;
+(p[D])	ld8  t9 = [src0], 3*8
+(p[D])	ld8 t11 = [src1], 3*8
+(p[D])	st8 [dst0] =  t6, 3*8
+(p[D])	st8 [dst1] = t10, 8
+	;;
+(p[D])	ld8 t12 = [src0], 8
+(p[D])	ld8 t14 = [src1], 8
+(p[D])	st8 [dst0] =  t9, 3*8
+(p[D])	st8 [dst1] = t11, 3*8
+	;;
+(p[D])	ld8 t13 = [src0], 4*8
+(p[D])	ld8 t15 = [src1], 4*8
+(p[D])	st8 [dst0] = t12, 8
+(p[D])	st8 [dst1] = t14, 8
+	;;
+(p[D-1])ld8  t1 = [src0], 8
+(p[D-1])ld8  t3 = [src1], 8
+(p[D])	st8 [dst0] = t13, 4*8
+(p[D])	st8 [dst1] = t15, 4*8
+	br.ctop.sptk .line_copy
+	;;
+	mov ar.lc = saved_lc
+	mov pr = saved_pr, -1
+	br.ret.sptk.many rp
+END(copy_page)

arch/ia64/lib/do_csum.S

@@ -8,9 +8,11 @@
  *	in0: address of buffer to checksum (char *)
  *	in1: length of the buffer (int)
  *
- * Copyright (C) 1999, 2001 Hewlett-Packard Co
- * Copyright (C) 1999 Stephane Eranian <eranian@hpl.hp.com>
+ * Copyright (C) 1999, 2001-2002 Hewlett-Packard Co
+ *	Stephane Eranian <eranian@hpl.hp.com>
  *
+ * 02/04/08	David Mosberger <davidm@hpl.hp.com>
+ *		More cleanup and tuning.
  * 01/04/18	Jun Nakajima <jun.nakajima@intel.com>
  *		Clean up and optimize and the software pipeline, loading two
  *		back-to-back 8-byte words per loop. Clean up the initialization
@@ -71,8 +73,6 @@
 //	calculating the Internet checksum.
 //
 // NOT YET DONE:
-//	- use the lfetch instruction to augment the chances of the data being in
-//	  the cache when we need it.
 //	- Maybe another algorithm which would take care of the folding at the
 //	  end in a different manner
 //	- Work with people more knowledgeable than me on the network stack
@@ -102,10 +102,6 @@
 #define buf		in0
 #define len		in1
 
-#ifndef CONFIG_IA64_LOAD_LATENCY
-#define CONFIG_IA64_LOAD_LATENCY	2
-#endif
-
 #define LOAD_LATENCY	2	// XXX fix me
 
 #if (LOAD_LATENCY != 1) && (LOAD_LATENCY != 2)
@@ -122,45 +118,46 @@ GLOBAL_ENTRY(do_csum)
 	.prologue
 	.save ar.pfs, saved_pfs
 	alloc saved_pfs=ar.pfs,2,16,1,16
-	.rotr word1[4], word2[4],result1[4],result2[4]
-	.rotp p[PIPE_DEPTH]
+	.rotr word1[4], word2[4],result1[LOAD_LATENCY+2],result2[LOAD_LATENCY+2]
+	.rotp p[PIPE_DEPTH], pC1[2], pC2[2]
 	mov ret0=r0		// in case we have zero length
 	cmp.lt p0,p6=r0,len	// check for zero length or negative (32bit len)
-	;;			// avoid WAW on CFM
-	mov tmp3=0x7		// a temporary mask/value
+	;;
 	add tmp1=buf,len	// last byte's address
-(p6)	br.ret.spnt.many rp	// return if true (hope we can avoid that)
+	.save pr, saved_pr
+	mov saved_pr=pr		// preserve predicates (rotation)
+(p6)	br.ret.spnt.many rp	// return if zero or negative length
 
-	and firstoff=7,buf	// how many bytes off for first1 element
-	tbit.nz p15,p0=buf,0	// is buf an odd address ?
 	mov hmask=-1		// intialize head mask
-	;;
-	andcm first1=buf,tmp3	// 8byte aligned down address of first1 element
+	tbit.nz p15,p0=buf,0	// is buf an odd address?
+	and first1=-8,buf	// 8-byte align down address of first1 element
+
+	and firstoff=7,buf	// how many bytes off for first1 element
 	mov tmask=-1		// initialize tail mask
-	adds tmp2=-1,tmp1	// last-1
+
 	;;
+	adds tmp2=-1,tmp1	// last-1
 	and lastoff=7,tmp1	// how many bytes off for last element
-	andcm last=tmp2,tmp3	// address of word containing last byte
-	.save pr, saved_pr
-	mov saved_pr=pr		// preserve predicates (rotation)
+	;;
+	sub tmp1=8,lastoff	// complement to lastoff
+	and last=-8,tmp2	// address of word containing last byte
 	;;
 	sub tmp3=last,first1	// tmp3=distance from first1 to last
+	.save ar.lc, saved_lc
+	mov saved_lc=ar.lc	// save lc
 	cmp.eq p8,p9=last,first1	// everything fits in one word ?
-	sub tmp1=8,lastoff	// complement to lastoff
-	ld8 firstval=[first1],8	// load,ahead of time, "first1" word
+
+	ld8 firstval=[first1],8	// load, ahead of time, "first1" word
+	and tmp1=7, tmp1	// make sure that if tmp1==8 -> tmp1=0
 	shl tmp2=firstoff,3	// number of bits
 	;;
-	and tmp1=7, tmp1	// make sure that if tmp1==8 -> tmp1=0
-(p9)	ld8 lastval=[last]	// load,ahead of time, "last" word, if needed
+(p9)	ld8 lastval=[last]	// load, ahead of time, "last" word, if needed
+	shl tmp1=tmp1,3		// number of bits
 (p9)	adds tmp3=-8,tmp3	// effectively loaded
 	;;
 (p8)	mov lastval=r0		// we don't need lastval if first1==last
-	shl tmp1=tmp1,3		// number of bits
 	shl hmask=hmask,tmp2	// build head mask, mask off [0,first1off[
-	;;
 	shr.u tmask=tmask,tmp1	// build tail mask, mask off ]8,lastoff]
-	.save ar.lc, saved_lc
-	mov saved_lc=ar.lc	// save lc
 	;;
 	.body
 #define count tmp3
@@ -171,8 +168,8 @@ GLOBAL_ENTRY(do_csum)
 	;;
 	// If count is odd, finish this 8-byte word so that we can
 	// load two back-to-back 8-byte words per loop thereafter.
-	tbit.nz p10,p11=count,0		// if (count is odd)
 	and word1[0]=firstval,hmask	// and mask it as appropriate
+	tbit.nz p10,p11=count,0		// if (count is odd)
 	;;
 (p8)	mov result1[0]=word1[0]
 (p9)	add result1[0]=word1[0],word2[0]
@@ -181,9 +178,8 @@ GLOBAL_ENTRY(do_csum)
 	;;
 (p6)	adds result1[0]=1,result1[0]
 (p8)	br.cond.dptk .do_csum_exit	// if (within an 8-byte word)
-	;;
 (p11)	br.cond.dptk .do_csum16		// if (count is even)
-	;;
+
 	// Here count is odd.
 	ld8 word1[1]=[first1],8		// load an 8-byte word
 	cmp.eq p9,p10=1,count		// if (count == 1)
@@ -194,11 +190,9 @@ GLOBAL_ENTRY(do_csum)
 	cmp.ltu p6,p0=result1[0],word1[1]
 	;;
 (p6)	adds result1[0]=1,result1[0]
-	;;
 (p9)	br.cond.sptk .do_csum_exit	// if (count == 1) exit
 	// Fall through to caluculate the checksum, feeding result1[0] as
 	// the initial value in result1[0].
-	;;
 	//
 	// Calculate the checksum loading two 8-byte words per loop.
 	//
@@ -207,45 +201,36 @@ GLOBAL_ENTRY(do_csum)
 	shr.u count=count,1	// we do 16 bytes per loop
 	;;
 	cmp.eq p9,p10=r0,count	// if (count == 0)
+	adds count=-1,count
 	brp.loop.imp 1f,2f
 	;;
-	adds count=-1,count
 	mov ar.ec=PIPE_DEPTH
-	;;
 	mov ar.lc=count	// set lc
-	;;
+
 	// result1[0] must be initialized in advance.
 	mov result2[0]=r0
-	;;
 	mov pr.rot=1<<16
-	;;
 	mov carry1=r0
 	mov carry2=r0
-	;;
 	add first2=8,first1
-	;;
 (p9)	br.cond.sptk .do_csum_exit
-	;;
-	nop.m	0
-	nop.i	0
 	;;
 	.align 32
 1:
-(ELD_1)	cmp.ltu p31,p0=result1[LOAD_LATENCY],word1[LOAD_LATENCY+1]
-(p32)	adds carry1=1,carry1
-(ELD_1)	cmp.ltu p47,p0=result2[LOAD_LATENCY],word2[LOAD_LATENCY+1]
-(p48)	adds carry2=1,carry2
+(ELD_1)	cmp.ltu pC1[0],p0=result1[LOAD_LATENCY],word1[LOAD_LATENCY+1]
+(pC1[1])adds carry1=1,carry1
+(ELD_1)	cmp.ltu pC2[0],p0=result2[LOAD_LATENCY],word2[LOAD_LATENCY+1]
+(pC2[1])adds carry2=1,carry2
 (ELD)	add result1[LOAD_LATENCY-1]=result1[LOAD_LATENCY],word1[LOAD_LATENCY]
 (ELD)	add result2[LOAD_LATENCY-1]=result2[LOAD_LATENCY],word2[LOAD_LATENCY]
-2:
-(p16)	ld8 word1[0]=[first1],16
-(p16)	ld8 word2[0]=[first2],16
+[2:]
+(p[0])	ld8 word1[0]=[first1],16
+(p[0])	ld8 word2[0]=[first2],16
 	br.ctop.sptk 1b
 	;;
-	// Since len is a 32-bit value, carry cannot be larger than
-	// a 64-bit value.
-(p32)	adds carry1=1,carry1	// since we miss the last one
-(p48)	adds carry2=1,carry2
+	// Since len is a 32-bit value, carry cannot be larger than a 64-bit value.
+(pC1[1])adds carry1=1,carry1	// since we miss the last one
+(pC2[1])adds carry2=1,carry2
 	;;
 	add result1[LOAD_LATENCY+1]=result1[LOAD_LATENCY+1],carry1
 	add result2[LOAD_LATENCY+1]=result2[LOAD_LATENCY+1],carry2
@@ -263,18 +248,15 @@ GLOBAL_ENTRY(do_csum)
 (p6)	adds result1[0]=1,result1[0]
 	;;
 .do_csum_exit:
-	movl tmp3=0xffffffff
-	;;
-	// XXX Fixme
 	//
 	// now fold 64 into 16 bits taking care of carry
 	// that's not very good because it has lots of sequentiality
 	//
-	and tmp1=result1[0],tmp3
+	mov tmp3=0xffff
+	zxt4 tmp1=result1[0]
 	shr.u tmp2=result1[0],32
 	;;
 	add result1[0]=tmp1,tmp2
-	shr.u tmp3=tmp3,16
 	;;
 	and tmp1=result1[0],tmp3
 	shr.u tmp2=result1[0],16

arch/ia64/lib/memset.S

@@ -9,8 +9,8 @@
  * 	in1:	byte value to use for storing
  *	in2:	length of the buffer
  *
- * Copyright (C) 1999, 2001 Hewlett-Packard Co
- * Copyright (C) 1999 Stephane Eranian <eranian@hpl.hp.com>
+ * Copyright (C) 1999, 2001, 2002 Hewlett-Packard Co
+ *	Stephane Eranian <eranian@hpl.hp.com>
  */
 
 #include <asm/asmmacro.h>
@@ -30,7 +30,19 @@
 #define saved_lc	r20
 #define tmp		r21
 
-GLOBAL_ENTRY(memset)
+GLOBAL_ENTRY(__bzero)
+	.prologue
+	.save ar.pfs, saved_pfs
+	alloc saved_pfs=ar.pfs,0,0,3,0
+	mov out2=out1
+	mov out1=0
+	/* FALL THROUGH (explicit NOPs so that next alloc is preceded by stop bit!) */
+	nop.m 0
+	nop.f 0
+	nop.i 0
+	;;
+END(__bzero)
+GLOBAL_ENTRY(__memset_generic)
 	.prologue
 	.save ar.pfs, saved_pfs
  	alloc saved_pfs=ar.pfs,3,0,0,0	// cnt is sink here
@@ -105,4 +117,7 @@ GLOBAL_ENTRY(memset)
 	;;
 (p6)	st1 [buf]=val		// only 1 byte left
 	br.ret.sptk.many rp
-END(memset)
+END(__memset_generic)
+
+	.global memset
+memset = __memset_generic		// alias needed for gcc

arch/ia64/lib/swiotlb.c

@@ -10,6 +10,7 @@
  *			unnecessary i-cache flushing.
  */
 
+#include <linux/cache.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/pci.h>
@@ -24,9 +25,6 @@
 #include <linux/init.h>
 #include <linux/bootmem.h>
 
-#define ALIGN(val, align) ((unsigned long)	\
-	(((unsigned long) (val) + ((align) - 1)) & ~((align) - 1)))
-
 #define OFFSET(val,align) ((unsigned long)	\
 	                   ( (val) & ( (align) - 1)))
 
@@ -276,7 +274,10 @@ swiotlb_alloc_consistent (struct pci_dev *hwdev, size_t size, dma_addr_t *dma_ha
 	int gfp = GFP_ATOMIC;
 	void *ret;
 
-	if (!hwdev || hwdev->dma_mask <= 0xffffffff)
+	/*
+	 * Alloc_consistent() is defined to return memory < 4GB, no matter what the DMA
+	 * mask says.
+	 */
 	gfp |= GFP_DMA; /* XXX fix me: should change this to GFP_32BIT or ZONE_32BIT */
 	ret = (void *)__get_free_pages(gfp, get_order(size));
 	if (!ret)

arch/ia64/mm/fault.c

@@ -120,15 +120,15 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	if (!(prev_vma && (prev_vma->vm_flags & VM_GROWSUP) && (address == prev_vma->vm_end))) {
 		if (!(vma->vm_flags & VM_GROWSDOWN))
 			goto bad_area;
-		if (rgn_index(address) != rgn_index(vma->vm_start)
-		    || rgn_offset(address) >= RGN_MAP_LIMIT)
+		if (REGION_NUMBER(address) != REGION_NUMBER(vma->vm_start)
+		    || REGION_OFFSET(address) >= RGN_MAP_LIMIT)
 			goto bad_area;
 		if (expand_stack(vma, address))
 			goto bad_area;
 	} else {
 		vma = prev_vma;
-		if (rgn_index(address) != rgn_index(vma->vm_start)
-		    || rgn_offset(address) >= RGN_MAP_LIMIT)
+		if (REGION_NUMBER(address) != REGION_NUMBER(vma->vm_start)
+		    || REGION_OFFSET(address) >= RGN_MAP_LIMIT)
 			goto bad_area;
 		if (expand_backing_store(vma, address))
 			goto bad_area;

arch/ia64/mm/init.c

@@ -40,10 +40,10 @@ static unsigned long totalram_pages;
 
 static int pgt_cache_water[2] = { 25, 50 };
 
-int
+void
 check_pgt_cache (void)
 {
-	int low, high, freed = 0;
+	int low, high;
 
 	low = pgt_cache_water[0];
 	high = pgt_cache_water[1];
@@ -51,12 +51,11 @@ check_pgt_cache (void)
 	if (pgtable_cache_size > high) {
 		do {
 			if (pgd_quicklist)
-				free_page((unsigned long)pgd_alloc_one_fast(0)), ++freed;
+				free_page((unsigned long)pgd_alloc_one_fast(0));
 			if (pmd_quicklist)
-				free_page((unsigned long)pmd_alloc_one_fast(0, 0)), ++freed;
+				free_page((unsigned long)pmd_alloc_one_fast(0, 0));
 		} while (pgtable_cache_size > low);
 	}
-	return freed;
 }
 
 /*
@@ -348,8 +347,6 @@ paging_init (void)
 {
 	unsigned long max_dma, zones_size[MAX_NR_ZONES];
 
-	clear_page((void *) ZERO_PAGE_ADDR);
-
 	/* initialize mem_map[] */
 
 	memset(zones_size, 0, sizeof(zones_size));

arch/ia64/mm/tlb.c

@@ -16,10 +16,11 @@
 #include <linux/smp.h>
 #include <linux/mm.h>
 
+#include <asm/delay.h>
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
 #include <asm/pal.h>
-#include <asm/delay.h>
+#include <asm/tlbflush.h>
 
 #define SUPPORTED_PGBITS (			\
 		1 << _PAGE_SIZE_256M |		\
@@ -79,7 +80,7 @@ wrap_mmu_context (struct mm_struct *mm)
 	flush_tlb_all();
 }
 
-static inline void
+void
 ia64_global_tlb_purge (unsigned long start, unsigned long end, unsigned long nbits)
 {
 	static spinlock_t ptcg_lock = SPIN_LOCK_UNLOCKED;

arch/ia64/vmlinux.lds.S

@@ -28,11 +28,6 @@ SECTIONS
   .text : AT(ADDR(.text) - PAGE_OFFSET)
     {
 	*(.text.ivt)
-	/* these are not really text pages, but they need to be page aligned: */
-	*(__special_page_section)
-	__start_gate_section = .;
-	*(.text.gate)
-	__stop_gate_section = .;
 	*(.text)
     }
   .text2 : AT(ADDR(.text2) - PAGE_OFFSET)
@@ -120,6 +115,13 @@ SECTIONS
   .data.init_task : AT(ADDR(.data.init_task) - PAGE_OFFSET)
 	{ *(.data.init_task) }
 
+  .data.page_aligned : AT(ADDR(.data.page_aligned) - PAGE_OFFSET)
+        { *(__special_page_section)
+	  __start_gate_section = .;
+	  *(.text.gate)
+	  __stop_gate_section = .;
+	}
+
   . = ALIGN(SMP_CACHE_BYTES);
   .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - PAGE_OFFSET)
         { *(.data.cacheline_aligned) }

drivers/pci/pci.ids

@@ -931,6 +931,9 @@
 	121a  NetServer SMIC Controller
 	121b  NetServer Legacy COM Port Decoder
 	121c  NetServer PCI COM Port Decoder
+	1229  zx1 System Bus Adapter
+	122a  zx1 I/O Controller
+	122e  zx1 Local Bus Adapter
 	2910  E2910A
 	2925  E2925A
 103e  Solliday Engineering

include/asm-ia64/acpi-ext.h

-#ifndef _ASM_IA64_ACPI_EXT_H
-#define _ASM_IA64_ACPI_EXT_H
-
-/*
- * Advanced Configuration and Power Infterface
- * Based on 'ACPI Specification 1.0b' Febryary 2, 1999
- * and 'IA-64 Extensions to the ACPI Specification' Rev 0.6
- *
- * Copyright (C) 1999 VA Linux Systems
- * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
- * Copyright (C) 2000 Intel Corp.
- * Copyright (C) 2000,2001 J.I. Lee <jung-ik.lee@intel.com>
- *	ACPI 2.0 specification
- */
-
-#include <linux/config.h>
-#include <linux/types.h>
-#include <linux/mm.h>
-
-#pragma	pack(1)
-#define ACPI_RSDP_SIG "RSD PTR " /* Trailing space required */
-#define ACPI_RSDP_SIG_LEN 8
-typedef struct {
-	char signature[8];
-	u8 checksum;
-	char oem_id[6];
-	u8 revision;
-	u32 rsdt;
-	u32 length;
-	struct acpi_xsdt *xsdt;
-	u8 ext_checksum;
-	u8 reserved[3];
-} acpi20_rsdp_t;
-
-typedef struct {
-	char signature[4];
-	u32 length;
-	u8 revision;
-	u8 checksum;
-	char oem_id[6];
-	char oem_table_id[8];
-	u32 oem_revision;
-	u32 creator_id;
-	u32 creator_revision;
-} acpi_desc_table_hdr_t;
-
-#define ACPI_RSDT_SIG "RSDT"
-#define ACPI_RSDT_SIG_LEN 4
-typedef struct {
-	acpi_desc_table_hdr_t header;
-	u8 reserved[4];
-	u32 entry_ptrs[1];	/* Not really . . . */
-} acpi20_rsdt_t;
-
-#define ACPI_XSDT_SIG "XSDT"
-#define ACPI_XSDT_SIG_LEN 4
-typedef struct acpi_xsdt {
-	acpi_desc_table_hdr_t header;
-	unsigned long entry_ptrs[1];	/* Not really . . . */
-} acpi_xsdt_t;
-
-/* Common structures for ACPI 2.0 and 0.71 */
-
-typedef struct acpi_entry_iosapic {
-	u8 type;
-	u8 length;
-	u8 id;
-	u8 reserved;
-	u32 irq_base;	/* start of IRQ's this IOSAPIC is responsible for. */
-	unsigned long address;	/* Address of this IOSAPIC */
-} acpi_entry_iosapic_t;
-
-/* Local SAPIC flags */
-#define LSAPIC_ENABLED                (1<<0)
-#define LSAPIC_PERFORMANCE_RESTRICTED (1<<1)
-#define LSAPIC_PRESENT                (1<<2)
-
-/* Defines legacy IRQ->pin mapping */
-typedef struct {
-	u8 type;
-	u8 length;
-	u8 bus;		/* Constant 0 == ISA */
-	u8 isa_irq;	/* ISA IRQ # */
-	u32 pin;		/* called vector in spec; really IOSAPIC pin number */
-	u16 flags;	/* Edge/Level trigger & High/Low active */
-} acpi_entry_int_override_t;
-
-#define INT_OVERRIDE_ACTIVE_LOW    0x03
-#define INT_OVERRIDE_LEVEL_TRIGGER 0x0d
-
-/* IA64 ext 0.71 */
-
-typedef struct {
-	char signature[8];
-	u8 checksum;
-	char oem_id[6];
-	char reserved;		/* Must be 0 */
-	struct acpi_rsdt *rsdt;
-} acpi_rsdp_t;
-
-typedef struct acpi_rsdt {
-	acpi_desc_table_hdr_t header;
-	u8 reserved[4];
-	unsigned long entry_ptrs[1];	/* Not really . . . */
-} acpi_rsdt_t;
-
-#define ACPI_SAPIC_SIG "SPIC"
-#define ACPI_SAPIC_SIG_LEN 4
-typedef struct {
-	acpi_desc_table_hdr_t header;
-	u8 reserved[4];
-	unsigned long interrupt_block;
-} acpi_sapic_t;
-
-/* SAPIC structure types */
-#define ACPI_ENTRY_LOCAL_SAPIC         0
-#define ACPI_ENTRY_IO_SAPIC            1
-#define ACPI_ENTRY_INT_SRC_OVERRIDE    2
-#define ACPI_ENTRY_PLATFORM_INT_SOURCE 3	/* Unimplemented */
-
-typedef struct acpi_entry_lsapic {
-	u8 type;
-	u8 length;
-	u16 acpi_processor_id;
-	u16 flags;
-	u8 id;
-	u8 eid;
-} acpi_entry_lsapic_t;
-
-typedef struct {
-	u8 type;
-	u8 length;
-	u16 flags;
-	u8 int_type;
-	u8 id;
-	u8 eid;
-	u8 iosapic_vector;
-	u8 reserved[4];
-	u32 global_vector;
-} acpi_entry_platform_src_t;
-
-/* ACPI 2.0 with 1.3 errata specific structures */
-
-#define ACPI_MADT_SIG "APIC"
-#define ACPI_MADT_SIG_LEN 4
-typedef struct {
-	acpi_desc_table_hdr_t header;
-	u32 lapic_address;
-	u32 flags;
-} acpi_madt_t;
-
-/* acpi 2.0 MADT flags */
-#define MADT_PCAT_COMPAT	(1<<0)
-
-/* acpi 2.0 MADT structure types */
-#define ACPI20_ENTRY_LOCAL_APIC			0
-#define ACPI20_ENTRY_IO_APIC			1
-#define ACPI20_ENTRY_INT_SRC_OVERRIDE		2
-#define ACPI20_ENTRY_NMI_SOURCE			3
-#define ACPI20_ENTRY_LOCAL_APIC_NMI		4
-#define ACPI20_ENTRY_LOCAL_APIC_ADDR_OVERRIDE	5
-#define ACPI20_ENTRY_IO_SAPIC			6
-#define ACPI20_ENTRY_LOCAL_SAPIC		7
-#define ACPI20_ENTRY_PLATFORM_INT_SOURCE	8
-
-typedef struct acpi20_entry_lsapic {
-	u8 type;
-	u8 length;
-	u8 acpi_processor_id;
-	u8 id;
-	u8 eid;
-	u8 reserved[3];
-	u32 flags;
-} acpi20_entry_lsapic_t;
-
-typedef struct acpi20_entry_lapic_addr_override {
-	u8 type;
-	u8 length;
-	u8 reserved[2];
-	unsigned long lapic_address;
-} acpi20_entry_lapic_addr_override_t;
-
-typedef struct {
-	u8 type;
-	u8 length;
-	u16 flags;
-	u8 int_type;
-	u8 id;
-	u8 eid;
-	u8 iosapic_vector;
-	u32 global_vector;
-} acpi20_entry_platform_src_t;
-
-/* constants for interrupt routing API for device drivers */
-#define ACPI20_ENTRY_PIS_PMI	1
-#define ACPI20_ENTRY_PIS_INIT	2
-#define ACPI20_ENTRY_PIS_CPEI	3
-#define ACPI_MAX_PLATFORM_IRQS	4
-
-#define ACPI_SPCRT_SIG	"SPCR"
-#define ACPI_SPCRT_SIG_LEN 4
-
-#define ACPI_DBGPT_SIG	"DBGP"
-#define ACPI_DBGPT_SIG_LEN 4
-
-extern int acpi20_parse(acpi20_rsdp_t *);
-extern int acpi20_early_parse(acpi20_rsdp_t *);
-extern int acpi_parse(acpi_rsdp_t *);
-extern const char *acpi_get_sysname (void);
-extern int acpi_request_vector(u32 int_type);
-extern void (*acpi_idle) (void);	/* power-management idle function, if any */
-#ifdef CONFIG_NUMA
-extern cnodeid_t paddr_to_nid(unsigned long paddr);
-#endif
-
-/*
- * ACPI 2.0 SRAT Table
- * http://www.microsoft.com/HWDEV/design/SRAT.htm
- */
-
-typedef struct acpi_srat {
-	acpi_desc_table_hdr_t header;
-	u32 table_revision;
-	u64 reserved;
-} acpi_srat_t;
-
-typedef struct srat_cpu_affinity {
-	u8 type;
-	u8 length;
-	u8 proximity_domain;
-	u8 apic_id;
-	u32 flags;
-	u8 local_sapic_eid;
-	u8 reserved[7];
-} srat_cpu_affinity_t;
-
-typedef struct srat_memory_affinity {
-	u8 type;
-	u8 length;
-	u8 proximity_domain;
-	u8 reserved[5];
-	u32 base_addr_lo;
-	u32 base_addr_hi;
-	u32 length_lo;
-	u32 length_hi;
-	u32 memory_type;
-	u32 flags;
-	u64 reserved2;
-} srat_memory_affinity_t;
-
-/* ACPI 2.0 SRAT structure */
-#define ACPI_SRAT_SIG "SRAT"
-#define ACPI_SRAT_SIG_LEN 4
-#define ACPI_SRAT_REVISION 1
-
-#define SRAT_CPU_STRUCTURE		0
-#define SRAT_MEMORY_STRUCTURE		1
-
-/* Only 1 flag for cpu affinity structure! */
-#define SRAT_CPU_FLAGS_ENABLED			0x00000001
-
-#define SRAT_MEMORY_FLAGS_ENABLED		0x00000001
-#define SRAT_MEMORY_FLAGS_HOTREMOVABLE		0x00000002
-
-/* ACPI 2.0 address range types */
-#define ACPI_ADDRESS_RANGE_MEMORY	1
-#define ACPI_ADDRESS_RANGE_RESERVED	2
-#define ACPI_ADDRESS_RANGE_ACPI		3
-#define ACPI_ADDRESS_RANGE_NVS		4
-
-#define NODE_ARRAY_INDEX(x)	((x) / 8)	/* 8 bits/char */
-#define NODE_ARRAY_OFFSET(x)	((x) % 8)	/* 8 bits/char */
-#define MAX_PXM_DOMAINS		(256)
-
-#ifdef CONFIG_DISCONTIGMEM
-/*
- * List of node memory chunks. Filled when parsing SRAT table to
- * obtain information about memory nodes.
-*/
-
-struct node_memory_chunk_s {
-	unsigned long start_paddr;
-	unsigned long size;
-	int pxm;			// proximity domain of node
-	int nid;			// which cnode contains this chunk?
-	int bank;			// which mem bank on this node
-};
-
-extern struct node_memory_chunk_s node_memory_chunk[PLAT_MAXCLUMPS];	// temporary?
-
-struct node_cpuid_s {
-	u16	phys_id;		/* id << 8 | eid */
-	int	pxm;			// proximity domain of cpu
-	int	nid;
-};
-extern struct node_cpuid_s node_cpuid[NR_CPUS];
-
-extern int pxm_to_nid_map[MAX_PXM_DOMAINS]; /* _PXM to logical node ID map */
-extern int nid_to_pxm_map[PLAT_MAX_COMPACT_NODES]; /* logical node ID to _PXM map */
-extern int numnodes;			/* total number of nodes in system */
-extern int num_memory_chunks;		/* total number of memory chunks */
-
-/*
- * ACPI 2.0 SLIT Table
- * http://devresource.hp.com/devresource/Docs/TechPapers/IA64/slit.pdf
- */
-
-typedef struct acpi_slit {
-	acpi_desc_table_hdr_t header;
-	u64 localities;
-	u8 entries[1];			/* dummy, real size = locality^2 */
-} acpi_slit_t;
-
-extern u8 acpi20_slit[PLAT_MAX_COMPACT_NODES * PLAT_MAX_COMPACT_NODES];
-
-#define ACPI_SLIT_SIG "SLIT"
-#define ACPI_SLIT_SIG_LEN 4
-#define ACPI_SLIT_REVISION 1
-#define ACPI_SLIT_LOCAL 10
-#endif /* CONFIG_DISCONTIGMEM */
-
-#pragma	pack()
-#endif /* _ASM_IA64_ACPI_EXT_H */

include/asm-ia64/acpi.h

+/*
+ *  asm-ia64/acpi.h
+ *
+ *  Copyright (C) 1999 VA Linux Systems
+ *  Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
+ *  Copyright (C) 2000,2001 J.I. Lee <jung-ik.lee@intel.com>
+ *  Copyright (C) 2001,2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#ifndef _ASM_ACPI_H
+#define _ASM_ACPI_H
+
+#ifdef __KERNEL__
+
+#define __acpi_map_table(phys_addr, size) __va(phys_addr)
+
+int acpi_boot_init (char *cdline);
+int acpi_find_rsdp (unsigned long *phys_addr);
+int acpi_request_vector (u32 int_type);
+int acpi_get_prt (struct pci_vector_struct **vectors, int *count);
+int acpi_get_interrupt_model(int *type);
+
+#ifdef CONFIG_DISCONTIGMEM
+#define NODE_ARRAY_INDEX(x)	((x) / 8)	/* 8 bits/char */
+#define NODE_ARRAY_OFFSET(x)	((x) % 8)	/* 8 bits/char */
+#define MAX_PXM_DOMAINS		(256)
+#endif /* CONFIG_DISCONTIGMEM */
+
+#endif /*__KERNEL__*/
+
+#endif /*_ASM_ACPI_H*/

include/asm-ia64/acpikcfg.h

-#ifndef _ASM_IA64_ACPIKCFG_H
-#define _ASM_IA64_ACPIKCFG_H
-
-/*
- *  acpikcfg.h - ACPI based Kernel Configuration Manager External Interfaces
- *
- *  Copyright (C) 2000 Intel Corp.
- *  Copyright (C) 2000 J.I. Lee  <jung-ik.lee@intel.com>
- */
-
-
-u32	__init acpi_cf_init (void * rsdp);
-u32	__init acpi_cf_terminate (void );
-
-u32	__init
-acpi_cf_get_pci_vectors (
-	struct pci_vector_struct	**vectors,
-	int				*num_pci_vectors
-	);
-
-
-#ifdef	CONFIG_ACPI_KERNEL_CONFIG_DEBUG
-void	__init
-acpi_cf_print_pci_vectors (
-	struct pci_vector_struct	*vectors,
-	int				num_pci_vectors
-	);
-#endif
-
-#endif /* _ASM_IA64_ACPIKCFG_H */

include/asm-ia64/cacheflush.h

+#ifndef _ASM_IA64_CACHEFLUSH_H
+#define _ASM_IA64_CACHEFLUSH_H
+
+/*
+ * Copyright (C) 2002 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ */
+
+#include <asm/bitops.h>
+#include <asm/page.h>
+
+/*
+ * Cache flushing routines.  This is the kind of stuff that can be very expensive, so try
+ * to avoid them whenever possible.
+ */
+
+#define flush_cache_all()			do { } while (0)
+#define flush_cache_mm(mm)			do { } while (0)
+#define flush_cache_range(vma, start, end)	do { } while (0)
+#define flush_cache_page(vma, vmaddr)		do { } while (0)
+#define flush_page_to_ram(page)			do { } while (0)
+#define flush_icache_page(vma,page)		do { } while (0)
+
+#define flush_dcache_page(page)			\
+do {						\
+	clear_bit(PG_arch_1, &page->flags);	\
+} while (0)
+
+extern void flush_icache_range (unsigned long start, unsigned long end);
+
+#define flush_icache_user_range(vma, page, user_addr, len)					\
+do {												\
+	unsigned long _addr = (unsigned long) page_address(page) + ((user_addr) & ~PAGE_MASK);	\
+	flush_icache_range(_addr, _addr + (len));						\
+} while (0)
+
+#endif /* _ASM_IA64_CACHEFLUSH_H */

include/asm-ia64/efi.h

@@ -87,6 +87,8 @@ typedef	struct {
 #define EFI_MEMORY_RUNTIME	0x8000000000000000	/* range requires runtime mapping */
 #define EFI_MEMORY_DESCRIPTOR_VERSION	1
 
+#define EFI_PAGE_SHIFT		12
+
 typedef struct {
 	u32 type;
 	u32 pad;
@@ -257,6 +259,7 @@ extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg);
 extern void efi_gettimeofday (struct timeval *tv);
 extern void efi_enter_virtual_mode (void);	/* switch EFI to virtual mode, if possible */
 extern u64  efi_get_iobase (void);
+extern u32  efi_mem_type (u64 phys_addr);
 
 /*
  * Variable Attributes

include/asm-ia64/hw_irq.h

@@ -88,6 +88,7 @@ hw_resend_irq (struct hw_interrupt_type *h, unsigned int vector)
 
 extern struct irq_desc _irq_desc[NR_IRQS];
 
+#ifndef CONFIG_IA64_GENERIC
 static inline struct irq_desc *
 __ia64_irq_desc (unsigned int irq)
 {
@@ -105,6 +106,7 @@ __ia64_local_vector_to_irq (ia64_vector vec)
 {
 	return (unsigned int) vec;
 }
+#endif
 
 /*
  * Next follows the irq descriptor interface.  On IA-64, each CPU supports 256 interrupt

include/asm-ia64/machvec.h

@@ -68,6 +68,8 @@ extern void machvec_noop (void);
 #  include <asm/machvec_hpsim.h>
 # elif defined (CONFIG_IA64_DIG)
 #  include <asm/machvec_dig.h>
+# elif defined (CONFIG_IA64_HP_ZX1)
+#  include <asm/machvec_hpzx1.h>
 # elif defined (CONFIG_IA64_SGI_SN1)
 #  include <asm/machvec_sn1.h>
 # elif defined (CONFIG_IA64_SGI_SN2)
@@ -123,6 +125,7 @@ struct ia64_machine_vector {
 	ia64_mv_cmci_handler_t *cmci_handler;
 	ia64_mv_log_print_t *log_print;
 	ia64_mv_send_ipi_t *send_ipi;
+	ia64_mv_global_tlb_purge_t *global_tlb_purge;
 	ia64_mv_pci_dma_init *dma_init;
 	ia64_mv_pci_alloc_consistent *alloc_consistent;
 	ia64_mv_pci_free_consistent *free_consistent;
@@ -149,6 +152,7 @@ struct ia64_machine_vector {
 {						\
 	#name,					\
 	platform_setup,				\
+	platform_cpu_init,			\
 	platform_irq_init,			\
 	platform_pci_fixup,			\
 	platform_map_nr,			\

include/asm-ia64/machvec_init.h

@@ -5,6 +5,11 @@
 #include <asm/machvec.h>
 
 extern ia64_mv_send_ipi_t ia64_send_ipi;
+extern ia64_mv_global_tlb_purge_t ia64_global_tlb_purge;
+extern ia64_mv_irq_desc __ia64_irq_desc;
+extern ia64_mv_irq_to_vector __ia64_irq_to_vector;
+extern ia64_mv_local_vector_to_irq __ia64_local_vector_to_irq;
+
 extern ia64_mv_inb_t __ia64_inb;
 extern ia64_mv_inw_t __ia64_inw;
 extern ia64_mv_inl_t __ia64_inl;