Revert ia64 changes from previous checkin.

Signed-off-by: Christian Limpach <Christian.Limpach@cl.cam.ac.uk>

9 files changed, 313 insertions, 227 deletions

diff --git a/linux-2.6-xen-sparse/arch/ia64/Kconfig b/linux-2.6-xen-sparse/arch/ia64/Kconfig
index 3b96f6ba80..a07c2964e1 100644
--- a/linux-2.6-xen-sparse/arch/ia64/Kconfig
+++ b/linux-2.6-xen-sparse/arch/ia64/Kconfig
@@ -26,6 +26,10 @@ config MMU
 	bool
 	default y
 
+config SWIOTLB
+       bool
+       default y
+
 config RWSEM_XCHGADD_ALGORITHM
 	bool
 	default y
@@ -97,16 +101,23 @@ config SCHED_NO_NO_OMIT_FRAME_POINTER
 	bool
 	default y
 
+config IA64_UNCACHED_ALLOCATOR
+	bool
+	select GENERIC_ALLOCATOR
+
+config DMA_IS_DMA32
+	bool
+	default y
+
 choice
 	prompt "System type"
 	default IA64_GENERIC
 
 config IA64_GENERIC
 	bool "generic"
+	select ACPI
 	select NUMA
 	select ACPI_NUMA
-	select VIRTUAL_MEM_MAP
-	select DISCONTIGMEM
 	help
 	  This selects the system type of your hardware.  A "generic" kernel
 	  will run on any supported IA-64 system.  However, if you configure
@@ -204,6 +215,21 @@ config IA64_PAGE_SIZE_64KB
 
 endchoice
 
+choice
+	prompt "Page Table Levels"
+	default PGTABLE_3
+
+config PGTABLE_3
+	bool "3 Levels"
+
+config PGTABLE_4
+	depends on !IA64_PAGE_SIZE_64KB
+	bool "4 Levels"
+
+endchoice
+
+source kernel/Kconfig.hz
+
 config IA64_BRL_EMU
 	bool
 	depends on ITANIUM
@@ -216,40 +242,6 @@ config IA64_L1_CACHE_SHIFT
 	default "6" if ITANIUM
 
 # align cache-sensitive data to 64 bytes
-config NUMA
-	bool "NUMA support"
-	depends on !IA64_HP_SIM
-	default y if IA64_SGI_SN2
-	select ACPI_NUMA
-	help
-	  Say Y to compile the kernel to support NUMA (Non-Uniform Memory
-	  Access).  This option is for configuring high-end multiprocessor
-	  server systems.  If in doubt, say N.
-
-config VIRTUAL_MEM_MAP
-	bool "Virtual mem map"
-	default y if !IA64_HP_SIM
-	help
-	  Say Y to compile the kernel with support for a virtual mem map.
-	  This code also only takes effect if a memory hole of greater than
-	  1 Gb is found during boot.  You must turn this option on if you
-	  require the DISCONTIGMEM option for your machine. If you are
-	  unsure, say Y.
-
-config HOLES_IN_ZONE
-	bool
-	default y if VIRTUAL_MEM_MAP
-
-config DISCONTIGMEM
-	bool "Discontiguous memory support"
-	depends on (IA64_DIG || IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB) && NUMA && VIRTUAL_MEM_MAP
-	default y if (IA64_SGI_SN2 || IA64_GENERIC) && NUMA
-	help
-	  Say Y to support efficient handling of discontiguous physical memory,
-	  for architectures which are either NUMA (Non-Uniform Memory Access)
-	  or have huge holes in the physical address space for other reasons.
-	  See <file:Documentation/vm/numa> for more.
-
 config IA64_CYCLONE
 	bool "Cyclone (EXA) Time Source support"
 	help
@@ -261,16 +253,10 @@ config IOSAPIC
 	depends on !IA64_HP_SIM
 	default y
 
-config IA64_SGI_SN_SIM
-	bool "SGI Medusa Simulator Support"
-	depends on IA64_SGI_SN2
-	help
-	  If you are compiling a kernel that will run under SGI's IA-64
-	  simulator (Medusa) then say Y, otherwise say N.
-
 config IA64_SGI_SN_XP
 	tristate "Support communication between SGI SSIs"
-	depends on MSPEC
+	depends on IA64_GENERIC || IA64_SGI_SN2
+	select IA64_UNCACHED_ALLOCATOR
 	help
 	  An SGI machine can be divided into multiple Single System
 	  Images which act independently of each other and have
@@ -279,8 +265,10 @@ config IA64_SGI_SN_XP
 	  based on a network adapter and DMA messaging.
 
 config FORCE_MAX_ZONEORDER
-	int
-	default "18"
+	int "MAX_ORDER (11 - 17)"  if !HUGETLB_PAGE
+	range 11 17  if !HUGETLB_PAGE
+	default "17" if HUGETLB_PAGE
+	default "11"
 
 config SMP
 	bool "Symmetric multi-processing support"
@@ -301,8 +289,8 @@ config SMP
 	  If you don't know what to do here, say N.
 
 config NR_CPUS
-	int "Maximum number of CPUs (2-512)"
-	range 2 512
+	int "Maximum number of CPUs (2-1024)"
+	range 2 1024
 	depends on SMP
 	default "64"
 	help
@@ -343,10 +331,59 @@ config PREEMPT
           Say Y here if you are building a kernel for a desktop, embedded
           or real-time system.  Say N if you are unsure.
 
-config HAVE_DEC_LOCK
+source "mm/Kconfig"
+
+config ARCH_SELECT_MEMORY_MODEL
+	def_bool y
+
+config ARCH_DISCONTIGMEM_ENABLE
+	def_bool y
+	help
+	  Say Y to support efficient handling of discontiguous physical memory,
+	  for architectures which are either NUMA (Non-Uniform Memory Access)
+	  or have huge holes in the physical address space for other reasons.
+ 	  See <file:Documentation/vm/numa> for more.
+
+config ARCH_FLATMEM_ENABLE
+	def_bool y
+
+config ARCH_SPARSEMEM_ENABLE
+	def_bool y
+	depends on ARCH_DISCONTIGMEM_ENABLE
+
+config ARCH_DISCONTIGMEM_DEFAULT
+	def_bool y if (IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB)
+	depends on ARCH_DISCONTIGMEM_ENABLE
+
+config NUMA
+	bool "NUMA support"
+	depends on !IA64_HP_SIM && !FLATMEM
+	default y if IA64_SGI_SN2
+	help
+	  Say Y to compile the kernel to support NUMA (Non-Uniform Memory
+	  Access).  This option is for configuring high-end multiprocessor
+	  server systems.  If in doubt, say N.
+
+# VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
+# VIRTUAL_MEM_MAP has been retained for historical reasons.
+config VIRTUAL_MEM_MAP
+	bool "Virtual mem map"
+	depends on !SPARSEMEM
+	default y if !IA64_HP_SIM
+	help
+	  Say Y to compile the kernel with support for a virtual mem map.
+	  This code also only takes effect if a memory hole of greater than
+	  1 Gb is found during boot.  You must turn this option on if you
+	  require the DISCONTIGMEM option for your machine. If you are
+	  unsure, say Y.
+
+config HOLES_IN_ZONE
 	bool
-	depends on (SMP || PREEMPT)
-	default y
+	default y if VIRTUAL_MEM_MAP
+
+config HAVE_ARCH_EARLY_PFN_TO_NID
+	def_bool y
+	depends on NEED_MULTIPLE_NODES
 
 config IA32_SUPPORT
 	bool "Support for Linux/x86 binaries"
@@ -384,11 +421,6 @@ config IA64_PALINFO
 	  To use this option, you have to ensure that the "/proc file system
 	  support" (CONFIG_PROC_FS) is enabled, too.
 
-config ACPI_DEALLOCATE_IRQ
-	bool
-	depends on IOSAPIC && EXPERIMENTAL
-	default y
-
 source "drivers/firmware/Kconfig"
 
 source "fs/Kconfig.binfmt"
@@ -397,36 +429,14 @@ endmenu
 
 menu "Power management and ACPI"
 
-config PM
-	bool "Power Management support"
-	depends on !IA64_HP_SIM
-	default y
-	help
-	  "Power Management" means that parts of your computer are shut
-	  off or put into a power conserving "sleep" mode if they are not
-	  being used.  There are two competing standards for doing this: APM
-	  and ACPI.  If you want to use either one, say Y here and then also
-	  to the requisite support below.
-
-	  Power Management is most important for battery powered laptop
-	  computers; if you have a laptop, check out the Linux Laptop home
-	  page on the WWW at <http://www.linux-on-laptops.com/> and the
-	  Battery Powered Linux mini-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
-
-	  Note that, even if you say N here, Linux on the x86 architecture
-	  will issue the hlt instruction if nothing is to be done, thereby
-	  sending the processor to sleep and saving power.
-
-config ACPI
-	bool
-	depends on !IA64_HP_SIM
-	default y
-
-if !IA64_HP_SIM
+source "kernel/power/Kconfig"
 
 source "drivers/acpi/Kconfig"
 
+if PM
+
+source "arch/ia64/kernel/cpufreq/Kconfig"
+
 endif
 
 endmenu
@@ -438,15 +448,8 @@ menu "Bus options (PCI, PCMCIA)"
 config PCI
 	bool "PCI support"
 	help
-	  Find out whether you have a PCI motherboard. PCI is the name of a
-	  bus system, i.e. the way the CPU talks to the other stuff inside
-	  your box. Other bus systems are ISA, EISA, MicroChannel (MCA) or
-	  VESA. If you have PCI, say Y, otherwise N.
-
-	  The PCI-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>, contains valuable
-	  information about which PCI hardware does work under Linux and which
-	  doesn't.
+	  Real IA-64 machines all have PCI/PCI-X/PCI Express busses.  Say Y
+	  here unless you are using a simulator without PCI support.
 
 config PCI_DOMAINS
 	bool
@@ -462,6 +465,8 @@ endmenu
 
 endif
 
+source "net/Kconfig"
+
 source "drivers/Kconfig"
 
 source "fs/Kconfig"
@@ -479,10 +484,28 @@ config GENERIC_IRQ_PROBE
 	bool
 	default y
 
+config GENERIC_PENDING_IRQ
+	bool
+	depends on GENERIC_HARDIRQS && SMP
+	default y
+
 source "arch/ia64/hp/sim/Kconfig"
 
+menu "Instrumentation Support"
+        depends on EXPERIMENTAL
+
 source "arch/ia64/oprofile/Kconfig"
 
+config KPROBES
+	bool "Kprobes (EXPERIMENTAL)"
+	help
+	  Kprobes allows you to trap at almost any kernel address and
+	  execute a callback function.  register_kprobe() establishes
+	  a probepoint and specifies the callback.  Kprobes is useful
+	  for kernel debugging, non-intrusive instrumentation and testing.
+	  If in doubt, say "N".
+endmenu
+
 source "arch/ia64/Kconfig.debug"
 
 source "security/Kconfig"
diff --git a/linux-2.6-xen-sparse/arch/ia64/Makefile b/linux-2.6-xen-sparse/arch/ia64/Makefile
index d1f780fc9e..1c597c27e3 100644
--- a/linux-2.6-xen-sparse/arch/ia64/Makefile
+++ b/linux-2.6-xen-sparse/arch/ia64/Makefile
@@ -11,9 +11,6 @@
 NM := $(CROSS_COMPILE)nm -B
 READELF := $(CROSS_COMPILE)readelf
 
-# following is temporary pending xen directory restructuring
-NOSTDINC_FLAGS += -Iinclude/asm-xen
-
 export AWK
 
 CHECKFLAGS	+= -m64 -D__ia64=1 -D__ia64__=1 -D_LP64 -D__LP64__
@@ -91,42 +88,7 @@ unwcheck: vmlinux
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
 
-CLEAN_FILES += include/asm-ia64/.offsets.h.stamp vmlinux.gz bootloader
-#CLEAN_FILES += include/asm-xen/xen-public include/asm-ia64/xen/asm-xsi-offsets.h
-#CLEAN_FILES += include/asm-xen/linux-public include/asm-xen/asm-ia64/hypervisor.h
-
-MRPROPER_FILES += include/asm-ia64/offsets.h
-
-prepare: include/asm-ia64/offsets.h
-
-arch/ia64/kernel/asm-offsets.s: include/asm include/linux/version.h include/config/MARKER
-
-include/asm-ia64/offsets.h: arch/ia64/kernel/asm-offsets.s
-	$(call filechk,gen-asm-offsets)
-
-arch/ia64/kernel/asm-offsets.s: include/asm-ia64/.offsets.h.stamp
-
-#XEN_PATH ?= $(srctree)/../xen-ia64-unstable.hg/
-include/asm-ia64/.offsets.h.stamp:
-	mkdir -p include/asm-ia64
-	[ -s include/asm-ia64/offsets.h ] \
-	 || echo "#define IA64_TASK_SIZE 0" > include/asm-ia64/offsets.h
-	touch $@
-	[ -e include/asm-xen/asm ] \
-	 || ln -s asm-ia64 include/asm-xen/asm
-#	[ -e include/asm-xen/xen-public ] \
-#	 || ln -s $(XEN_PATH)/xen/include/public \
-#		include/asm-xen/xen-public
-#	[ -e include/asm-ia64/xen/asm-xsi-offsets.h ] \
-#	 || ln -s $(XEN_PATH)/xen/include/asm-ia64/asm-xsi-offsets.h \
-#		include/asm-ia64/xen/asm-xsi-offsets.h
-#	[ -e include/asm-xen/linux-public ] \
-#	 || ln -s $(XEN_PATH)/linux-2.6-xen-sparse/include/asm-xen/linux-public \
-		include/asm-xen/linux-public
-	[ -e include/asm-xen/asm-ia64/hypervisor.h ] \
-	 || ln -s $(XEN_PATH)/linux-2.6-xen-sparse/include/asm-xen/asm-ia64/hypervisor.h \
-		include/asm-xen/asm-ia64/hypervisor.h
-
+CLEAN_FILES += vmlinux.gz bootloader
 
 boot:	lib/lib.a vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $@
diff --git a/linux-2.6-xen-sparse/arch/ia64/kernel/entry.S b/linux-2.6-xen-sparse/arch/ia64/kernel/entry.S
index c77200dcc0..bd1f340774 100644
--- a/linux-2.6-xen-sparse/arch/ia64/kernel/entry.S
+++ b/linux-2.6-xen-sparse/arch/ia64/kernel/entry.S
@@ -37,7 +37,7 @@
 #include <asm/cache.h>
 #include <asm/errno.h>
 #include <asm/kregs.h>
-#include <asm/offsets.h>
+#include <asm/asm-offsets.h>
 #include <asm/pgtable.h>
 #include <asm/percpu.h>
 #include <asm/processor.h>
@@ -204,9 +204,6 @@ GLOBAL_ENTRY(__ia64_switch_to)
 (p6)	br.cond.dpnt .map
 	;;
 .done:
-(p6)	ssm psr.ic			// if we had to map, reenable the psr.ic bit FIRST!!!
-	;;
-(p6)	srlz.d
 	ld8 sp=[r21]			// load kernel stack pointer of new task
 	mov IA64_KR(CURRENT)=in0	// update "current" application register
 	mov r8=r13			// return pointer to previously running task
@@ -234,6 +231,9 @@ GLOBAL_ENTRY(__ia64_switch_to)
 	mov IA64_KR(CURRENT_STACK)=r26	// remember last page we mapped...
 	;;
 	itr.d dtr[r25]=r23		// wire in new mapping...
+	ssm psr.ic			// reenable the psr.ic bit
+	;;
+	srlz.d
 	br.cond.sptk .done
 END(__ia64_switch_to)
 
@@ -470,17 +470,28 @@ GLOBAL_ENTRY(load_switch_stack)
 	br.cond.sptk.many b7
 END(load_switch_stack)
 
-GLOBAL_ENTRY(__ia64_syscall)
-	.regstk 6,0,0,0
-	mov r15=in5				// put syscall number in place
-	break __BREAK_SYSCALL
-	movl r2=errno
-	cmp.eq p6,p7=-1,r10
+GLOBAL_ENTRY(prefetch_stack)
+	add r14 = -IA64_SWITCH_STACK_SIZE, sp
+	add r15 = IA64_TASK_THREAD_KSP_OFFSET, in0
+	;;
+	ld8 r16 = [r15]				// load next's stack pointer
+	lfetch.fault.excl [r14], 128
+	;;
+	lfetch.fault.excl [r14], 128
+	lfetch.fault [r16], 128
+	;;
+	lfetch.fault.excl [r14], 128
+	lfetch.fault [r16], 128
+	;;
+	lfetch.fault.excl [r14], 128
+	lfetch.fault [r16], 128
 	;;
-(p6)	st4 [r2]=r8
-(p6)	mov r8=-1
+	lfetch.fault.excl [r14], 128
+	lfetch.fault [r16], 128
+	;;
+	lfetch.fault [r16], 128
 	br.ret.sptk.many rp
-END(__ia64_syscall)
+END(prefetch_stack)
 
 GLOBAL_ENTRY(execve)
 	mov r15=__NR_execve			// put syscall number in place
@@ -640,7 +651,7 @@ END(ia64_ret_from_syscall)
  *	      r8-r11: restored (syscall return value(s))
  *		 r12: restored (user-level stack pointer)
  *		 r13: restored (user-level thread pointer)
- *		 r14: cleared
+ *		 r14: set to __kernel_syscall_via_epc
  *		 r15: restored (syscall #)
  *	     r16-r17: cleared
  *		 r18: user-level b6
@@ -661,7 +672,7 @@ END(ia64_ret_from_syscall)
  *		  pr: restored (user-level pr)
  *		  b0: restored (user-level rp)
  *	          b6: restored
- *		  b7: cleared
+ *		  b7: set to __kernel_syscall_via_epc
  *	     ar.unat: restored (user-level ar.unat)
  *	      ar.pfs: restored (user-level ar.pfs)
  *	      ar.rsc: restored (user-level ar.rsc)
@@ -707,72 +718,79 @@ GLOBAL_ENTRY(__ia64_leave_syscall)
 	;;
 (p6)	ld4 r31=[r18]				// load current_thread_info()->flags
 	ld8 r19=[r2],PT(B6)-PT(LOADRS)		// load ar.rsc value for "loadrs"
-	mov b7=r0		// clear b7
+	nop.i 0
 	;;
-	ld8 r23=[r3],PT(R11)-PT(AR_BSPSTORE)	// load ar.bspstore (may be garbage)
+	mov r16=ar.bsp				// M2  get existing backing store pointer
 	ld8 r18=[r2],PT(R9)-PT(B6)		// load b6
 (p6)	and r15=TIF_WORK_MASK,r31		// any work other than TIF_SYSCALL_TRACE?
 	;;
-	mov r16=ar.bsp				// M2  get existing backing store pointer
+	ld8 r23=[r3],PT(R11)-PT(AR_BSPSTORE)	// load ar.bspstore (may be garbage)
 (p6)	cmp4.ne.unc p6,p0=r15, r0		// any special work pending?
 (p6)	br.cond.spnt .work_pending_syscall
 	;;
 	// start restoring the state saved on the kernel stack (struct pt_regs):
 	ld8 r9=[r2],PT(CR_IPSR)-PT(R9)
 	ld8 r11=[r3],PT(CR_IIP)-PT(R11)
-	mov f6=f0		// clear f6
+(pNonSys) break 0		//      bug check: we shouldn't be here if pNonSys is TRUE!
 	;;
 	invala			// M0|1 invalidate ALAT
-	rsm psr.i | psr.ic	// M2 initiate turning off of interrupt and interruption collection
-	mov f9=f0		// clear f9
+	rsm psr.i | psr.ic	// M2   turn off interrupts and interruption collection
+	cmp.eq p9,p0=r0,r0	// A    set p9 to indicate that we should restore cr.ifs
 
-	ld8 r29=[r2],16		// load cr.ipsr
-	ld8 r28=[r3],16			// load cr.iip
-	mov f8=f0		// clear f8
+	ld8 r29=[r2],16		// M0|1 load cr.ipsr
+	ld8 r28=[r3],16		// M0|1 load cr.iip
+	mov r22=r0		// A    clear r22
 	;;
 	ld8 r30=[r2],16		// M0|1 load cr.ifs
 	ld8 r25=[r3],16		// M0|1 load ar.unat
-	cmp.eq p9,p0=r0,r0	// set p9 to indicate that we should restore cr.ifs
+(pUStk) add r14=IA64_TASK_THREAD_ON_USTACK_OFFSET,r13
 	;;
 	ld8 r26=[r2],PT(B0)-PT(AR_PFS)	// M0|1 load ar.pfs
-(pKStk)	mov r22=psr		// M2 read PSR now that interrupts are disabled
-	mov f10=f0		// clear f10
+(pKStk)	mov r22=psr			// M2   read PSR now that interrupts are disabled
+	nop 0
 	;;
-	ld8 r21=[r2],PT(AR_RNAT)-PT(B0) // load b0
-	ld8 r27=[r3],PT(PR)-PT(AR_RSC)	// load ar.rsc
-	mov f11=f0		// clear f11
+	ld8 r21=[r2],PT(AR_RNAT)-PT(B0) // M0|1 load b0
+	ld8 r27=[r3],PT(PR)-PT(AR_RSC)	// M0|1 load ar.rsc
+	mov f6=f0			// F    clear f6
 	;;
-	ld8 r24=[r2],PT(AR_FPSR)-PT(AR_RNAT)	// load ar.rnat (may be garbage)
-	ld8 r31=[r3],PT(R1)-PT(PR)		// load predicates
-(pUStk) add r14=IA64_TASK_THREAD_ON_USTACK_OFFSET,r13
+	ld8 r24=[r2],PT(AR_FPSR)-PT(AR_RNAT)	// M0|1 load ar.rnat (may be garbage)
+	ld8 r31=[r3],PT(R1)-PT(PR)		// M0|1 load predicates
+	mov f7=f0				// F    clear f7
 	;;
-	ld8 r20=[r2],PT(R12)-PT(AR_FPSR)	// load ar.fpsr
-	ld8.fill r1=[r3],16	// load r1
-(pUStk) mov r17=1
+	ld8 r20=[r2],PT(R12)-PT(AR_FPSR)	// M0|1 load ar.fpsr
+	ld8.fill r1=[r3],16			// M0|1 load r1
+(pUStk) mov r17=1				// A
 	;;
-	srlz.d			// M0  ensure interruption collection is off
-	ld8.fill r13=[r3],16
-	mov f7=f0		// clear f7
+(pUStk) st1 [r14]=r17				// M2|3
+	ld8.fill r13=[r3],16			// M0|1
+	mov f8=f0				// F    clear f8
 	;;
-	ld8.fill r12=[r2]	// restore r12 (sp)
-	mov.m ar.ssd=r0		// M2 clear ar.ssd
-	mov r22=r0		// clear r22
+	ld8.fill r12=[r2]			// M0|1 restore r12 (sp)
+	ld8.fill r15=[r3]			// M0|1 restore r15
+	mov b6=r18				// I0   restore b6
 
-	ld8.fill r15=[r3]	// restore r15
-(pUStk) st1 [r14]=r17
-	addl r3=THIS_CPU(ia64_phys_stacked_size_p8),r0
+	addl r17=THIS_CPU(ia64_phys_stacked_size_p8),r0 // A
+	mov f9=f0					// F    clear f9
+(pKStk) br.cond.dpnt.many skip_rbs_switch		// B
+
+	srlz.d				// M0   ensure interruption collection is off (for cover)
+	shr.u r18=r19,16		// I0|1 get byte size of existing "dirty" partition
+	cover				// B    add current frame into dirty partition & set cr.ifs
 	;;
-(pUStk)	ld4 r17=[r3]		// r17 = cpu_data->phys_stacked_size_p8
-	mov.m ar.csd=r0		// M2 clear ar.csd
-	mov b6=r18		// I0  restore b6
+(pUStk) ld4 r17=[r17]			// M0|1 r17 = cpu_data->phys_stacked_size_p8
+	mov r19=ar.bsp			// M2   get new backing store pointer
+	mov f10=f0			// F    clear f10
+
+	nop.m 0
+	movl r14=__kernel_syscall_via_epc // X
 	;;
-	mov r14=r0		// clear r14
-	shr.u r18=r19,16	// I0|1 get byte size of existing "dirty" partition
-(pKStk) br.cond.dpnt.many skip_rbs_switch
+	mov.m ar.csd=r0			// M2   clear ar.csd
+	mov.m ar.ccv=r0			// M2   clear ar.ccv
+	mov b7=r14			// I0   clear b7 (hint with __kernel_syscall_via_epc)
 
-	mov.m ar.ccv=r0		// clear ar.ccv
-(pNonSys) br.cond.dpnt.many dont_preserve_current_frame
-	br.cond.sptk.many rbs_switch
+	mov.m ar.ssd=r0			// M2   clear ar.ssd
+	mov f11=f0			// F    clear f11
+	br.cond.sptk.many rbs_switch	// B
 END(__ia64_leave_syscall)
 
 #ifdef CONFIG_IA32_SUPPORT
@@ -891,7 +909,7 @@ GLOBAL_ENTRY(__ia64_leave_kernel)
 	ldf.fill f7=[r2],PT(F11)-PT(F7)
 	ldf.fill f8=[r3],32
 	;;
-	srlz.i			// ensure interruption collection is off
+	srlz.d	// ensure that inter. collection is off (VHPT is don't care, since text is pinned)
 	mov ar.ccv=r15
 	;;
 	ldf.fill f11=[r2]
@@ -951,11 +969,10 @@ GLOBAL_ENTRY(__ia64_leave_kernel)
 	 * NOTE: alloc, loadrs, and cover can't be predicated.
 	 */
 (pNonSys) br.cond.dpnt dont_preserve_current_frame
-
-rbs_switch:
 	cover				// add current frame into dirty partition and set cr.ifs
 	;;
 	mov r19=ar.bsp			// get new backing store pointer
+rbs_switch:
 	sub r16=r16,r18			// krbs = old bsp - size of dirty partition
 	cmp.ne p9,p0=r0,r0		// clear p9 to skip restore of cr.ifs
 	;;
@@ -1030,14 +1047,14 @@ rse_clear_invalid:
 	mov loc5=0
 	mov loc6=0
 	mov loc7=0
-(pRecurse) br.call.sptk.few b0=rse_clear_invalid
+(pRecurse) br.call.dptk.few b0=rse_clear_invalid
 	;;
 	mov loc8=0
 	mov loc9=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 b0
+(pReturn) br.ret.dptk.many b0
 #endif /* !CONFIG_ITANIUM */
 #	undef pRecurse
 #	undef pReturn
@@ -1261,7 +1278,7 @@ ENTRY(sys_rt_sigreturn)
  	stf.spill [r17]=f11
 	adds out0=16,sp				// out0 = &sigscratch
 	br.call.sptk.many rp=ia64_rt_sigreturn
-.ret19:	.restore sp 0
+.ret19:	.restore sp,0
 	adds sp=16,sp
 	;;
 	ld8 r9=[sp]				// load new ar.unat
@@ -1583,11 +1600,11 @@ sys_call_table:
 	data8 sys_add_key
 	data8 sys_request_key
 	data8 sys_keyctl
+	data8 sys_ioprio_set
+	data8 sys_ioprio_get			// 1275
 	data8 sys_ni_syscall
-	data8 sys_ni_syscall			// 1275
-	data8 sys_ni_syscall
-	data8 sys_ni_syscall
-	data8 sys_ni_syscall
-	data8 sys_ni_syscall
+	data8 sys_inotify_init
+	data8 sys_inotify_add_watch
+	data8 sys_inotify_rm_watch
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
diff --git a/linux-2.6-xen-sparse/arch/ia64/kernel/head.S b/linux-2.6-xen-sparse/arch/ia64/kernel/head.S
index 222a68d1cf..78d2b50361 100644
--- a/linux-2.6-xen-sparse/arch/ia64/kernel/head.S
+++ b/linux-2.6-xen-sparse/arch/ia64/kernel/head.S
@@ -25,7 +25,7 @@
 #include <asm/fpu.h>
 #include <asm/kregs.h>
 #include <asm/mmu_context.h>
-#include <asm/offsets.h>
+#include <asm/asm-offsets.h>
 #include <asm/pal.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
diff --git a/linux-2.6-xen-sparse/arch/ia64/kernel/setup.c b/linux-2.6-xen-sparse/arch/ia64/kernel/setup.c
index 3fcff8996a..177809c79b 100644
--- a/linux-2.6-xen-sparse/arch/ia64/kernel/setup.c
+++ b/linux-2.6-xen-sparse/arch/ia64/kernel/setup.c
@@ -20,6 +20,7 @@
  * 02/01/00 R.Seth	fixed get_cpuinfo for SMP
  * 01/07/99 S.Eranian	added the support for command line argument
  * 06/24/99 W.Drummond	added boot_cpu_data.
+ * 05/28/05 Z. Menyhart	Dynamic stride size for "flush_icache_range()"
  */
 #include <linux/config.h>
 #include <linux/module.h>
@@ -40,6 +41,8 @@
 #include <linux/serial_core.h>
 #include <linux/efi.h>
 #include <linux/initrd.h>
+#include <linux/platform.h>
+#include <linux/pm.h>
 
 #include <asm/ia32.h>
 #include <asm/machvec.h>
@@ -72,8 +75,30 @@ DEFINE_PER_CPU(unsigned long, ia64_phys_stacked_size_p8);
 unsigned long ia64_cycles_per_usec;
 struct ia64_boot_param *ia64_boot_param;
 struct screen_info screen_info;
+unsigned long vga_console_iobase;
+unsigned long vga_console_membase;
+
+static struct resource data_resource = {
+	.name	= "Kernel data",
+	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+};
+
+static struct resource code_resource = {
+	.name	= "Kernel code",
+	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+};
+extern void efi_initialize_iomem_resources(struct resource *,
+		struct resource *);
+extern char _text[], _end[], _etext[];
 
 unsigned long ia64_max_cacheline_size;
+
+int dma_get_cache_alignment(void)
+{
+        return ia64_max_cacheline_size;
+}
+EXPORT_SYMBOL(dma_get_cache_alignment);
+
 unsigned long ia64_iobase;	/* virtual address for I/O accesses */
 EXPORT_SYMBOL(ia64_iobase);
 struct io_space io_space[MAX_IO_SPACES];
@@ -81,6 +106,13 @@ EXPORT_SYMBOL(io_space);
 unsigned int num_io_spaces;
 
 /*
+ * "flush_icache_range()" needs to know what processor dependent stride size to use
+ * when it makes i-cache(s) coherent with d-caches.
+ */
+#define	I_CACHE_STRIDE_SHIFT	5	/* Safest way to go: 32 bytes by 32 bytes */
+unsigned long ia64_i_cache_stride_shift = ~0;
+
+/*
  * The merge_mask variable needs to be set to (max(iommu_page_size(iommu)) - 1).  This
  * mask specifies a mask of address bits that must be 0 in order for two buffers to be
  * mergeable by the I/O MMU (i.e., the end address of the first buffer and the start
@@ -159,6 +191,22 @@ sort_regions (struct rsvd_region *rsvd_region, int max)
 	}
 }
 
+/*
+ * Request address space for all standard resources
+ */
+static int __init register_memory(void)
+{
+	code_resource.start = ia64_tpa(_text);
+	code_resource.end   = ia64_tpa(_etext) - 1;
+	data_resource.start = ia64_tpa(_etext);
+	data_resource.end   = ia64_tpa(_end) - 1;
+	efi_initialize_iomem_resources(&code_resource, &data_resource);
+
+	return 0;
+}
+
+__initcall(register_memory);
+
 /**
  * reserve_memory - setup reserved memory areas
  *
@@ -199,6 +247,9 @@ reserve_memory (void)
 	}
 #endif
 
+	efi_memmap_init(&rsvd_region[n].start, &rsvd_region[n].end);
+	n++;
+
 	/* end of memory marker */
 	rsvd_region[n].start = ~0UL;
 	rsvd_region[n].end   = ~0UL;
@@ -232,28 +283,31 @@ find_initrd (void)
 static void __init
 io_port_init (void)
 {
-	extern unsigned long ia64_iobase;
 	unsigned long phys_iobase;
 
 	/*
-	 *  Set `iobase' to the appropriate address in region 6 (uncached access range).
+	 * Set `iobase' based on the EFI memory map or, failing that, the
+	 * value firmware left in ar.k0.
+	 *
+	 * Note that in ia32 mode, IN/OUT instructions use ar.k0 to compute
+	 * the port's virtual address, so ia32_load_state() loads it with a
+	 * user virtual address.  But in ia64 mode, glibc uses the
+	 * *physical* address in ar.k0 to mmap the appropriate area from
+	 * /dev/mem, and the inX()/outX() interfaces use MMIO.  In both
+	 * cases, user-mode can only use the legacy 0-64K I/O port space.
 	 *
-	 *  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.
+	 * ar.k0 is not involved in kernel I/O port accesses, which can use
+	 * any of the I/O port spaces and are done via MMIO using the
+	 * virtual mmio_base from the appropriate io_space[].
 	 */
 	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, phys_iobase);
-	else {
+	if (!phys_iobase) {
 		phys_iobase = ia64_get_kr(IA64_KR_IO_BASE);
-		printk(KERN_INFO "No I/O port range found in EFI memory map, falling back "
-		       "to AR.KR0\n");
-		printk(KERN_INFO "I/O port base = 0x%lx\n", phys_iobase);
+		printk(KERN_INFO "No I/O port range found in EFI memory map, "
+			"falling back to AR.KR0 (0x%lx)\n", phys_iobase);
 	}
 	ia64_iobase = (unsigned long) ioremap(phys_iobase, 0);
+	ia64_set_kr(IA64_KR_IO_BASE, __pa(ia64_iobase));
 
 	/* setup legacy IO port space */
 	io_space[0].mmio_base = ia64_iobase;
@@ -273,26 +327,29 @@ io_port_init (void)
 static inline int __init
 early_console_setup (char *cmdline)
 {
+	int earlycons = 0;
+
 #ifdef CONFIG_XEN
-	if (!early_xen_console_setup(cmdline)) return 0;
+	if (!early_xen_console_setup(cmdline))
+		earlycons++;
 #endif
 #ifdef CONFIG_SERIAL_SGI_L1_CONSOLE
 	{
 		extern int sn_serial_console_early_setup(void);
 		if (!sn_serial_console_early_setup())
-			return 0;
+			earlycons++;
 	}
 #endif
 #ifdef CONFIG_EFI_PCDP
 	if (!efi_setup_pcdp_console(cmdline))
-		return 0;
+		earlycons++;
 #endif
 #ifdef CONFIG_SERIAL_8250_CONSOLE
 	if (!early_serial_console_init(cmdline))
-		return 0;
+		earlycons++;
 #endif
 
-	return -1;
+	return (earlycons) ? 0 : -1;
 }
 
 static inline void
@@ -373,7 +430,7 @@ setup_arch (char **cmdline_p)
 	if (early_console_setup(*cmdline_p) == 0)
 		mark_bsp_online();
 
-#ifdef CONFIG_ACPI_BOOT
+#ifdef CONFIG_ACPI
 	/* Initialize the ACPI boot-time table parser */
 	acpi_table_init();
 # ifdef CONFIG_ACPI_NUMA
@@ -408,8 +465,9 @@ setup_arch (char **cmdline_p)
 #endif
 
 	cpu_init();	/* initialize the bootstrap CPU */
+	mmu_context_init();	/* initialize context_id bitmap */
 
-#ifdef CONFIG_ACPI_BOOT
+#ifdef CONFIG_ACPI
 	acpi_boot_init();
 #endif
 
@@ -515,7 +573,7 @@ show_cpuinfo (struct seq_file *m, void *v)
 		   c->itc_freq / 1000000, c->itc_freq % 1000000,
 		   lpj*HZ/500000, (lpj*HZ/5000) % 100);
 #ifdef CONFIG_SMP
-	seq_printf(m, "siblings   : %u\n", c->num_log);
+	seq_printf(m, "siblings   : %u\n", cpus_weight(cpu_core_map[cpunum]));
 	if (c->threads_per_core > 1 || c->cores_per_socket > 1)
 		seq_printf(m,
 		   	   "physical id: %u\n"
@@ -625,6 +683,12 @@ setup_per_cpu_areas (void)
 	/* start_kernel() requires this... */
 }
 
+/*
+ * Calculate the max. cache line size.
+ *
+ * In addition, the minimum of the i-cache stride sizes is calculated for
+ * "flush_icache_range()".
+ */
 static void
 get_max_cacheline_size (void)
 {
@@ -638,6 +702,8 @@ get_max_cacheline_size (void)
                 printk(KERN_ERR "%s: ia64_pal_cache_summary() failed (status=%ld)\n",
                        __FUNCTION__, status);
                 max = SMP_CACHE_BYTES;
+		/* Safest setup for "flush_icache_range()" */
+		ia64_i_cache_stride_shift = I_CACHE_STRIDE_SHIFT;
 		goto out;
         }
 
@@ -646,14 +712,31 @@ get_max_cacheline_size (void)
 						    &cci);
 		if (status != 0) {
 			printk(KERN_ERR
-			       "%s: ia64_pal_cache_config_info(l=%lu) failed (status=%ld)\n",
+			       "%s: ia64_pal_cache_config_info(l=%lu, 2) failed (status=%ld)\n",
 			       __FUNCTION__, l, status);
 			max = SMP_CACHE_BYTES;
+			/* The safest setup for "flush_icache_range()" */
+			cci.pcci_stride = I_CACHE_STRIDE_SHIFT;
+			cci.pcci_unified = 1;
 		}
 		line_size = 1 << cci.pcci_line_size;
 		if (line_size > max)
 			max = line_size;
-        }
+		if (!cci.pcci_unified) {
+			status = ia64_pal_cache_config_info(l,
+						    /* cache_type (instruction)= */ 1,
+						    &cci);
+			if (status != 0) {
+				printk(KERN_ERR
+				"%s: ia64_pal_cache_config_info(l=%lu, 1) failed (status=%ld)\n",
+					__FUNCTION__, l, status);
+				/* The safest setup for "flush_icache_range()" */
+				cci.pcci_stride = I_CACHE_STRIDE_SHIFT;
+			}
+		}
+		if (cci.pcci_stride < ia64_i_cache_stride_shift)
+			ia64_i_cache_stride_shift = cci.pcci_stride;
+	}
   out:
 	if (max > ia64_max_cacheline_size)
 		ia64_max_cacheline_size = max;
@@ -782,6 +865,7 @@ cpu_init (void)
 	/* size of physical stacked register partition plus 8 bytes: */
 	__get_cpu_var(ia64_phys_stacked_size_p8) = num_phys_stacked*8 + 8;
 	platform_cpu_init();
+	pm_idle = default_idle;
 }
 
 void
diff --git a/linux-2.6-xen-sparse/arch/ia64/xen-mkbuildtree-pre b/linux-2.6-xen-sparse/arch/ia64/xen-mkbuildtree-pre
index 6e63488616..05226b3cfa 100755
--- a/linux-2.6-xen-sparse/arch/ia64/xen-mkbuildtree-pre
+++ b/linux-2.6-xen-sparse/arch/ia64/xen-mkbuildtree-pre
@@ -13,10 +13,10 @@ then
 	mv net net.xen-x86
 	mv kernel kernel.xen-x86
 	mv drivers/acpi/tables.c drivers/acpi/tables.c.xen-x86
-	mv arch/xen/kernel drivers/xen/core
-	mv arch/xen arch/xen.xen-x86
-	mkdir arch/xen
-	mv arch/xen.xen-x86/configs arch/xen
+#	mv arch/xen/kernel drivers/xen/core
+#	mv arch/xen arch/xen.xen-x86
+#	mkdir arch/xen
+#	mv arch/xen.xen-x86/configs arch/xen
 #	mv include/asm-generic include/asm-generic.xen-x86
 	mv include/linux include/linux.xen-x86
 	mkdir include/linux
diff --git a/linux-2.6-xen-sparse/arch/ia64/xen/drivers/evtchn_ia64.c b/linux-2.6-xen-sparse/arch/ia64/xen/drivers/evtchn_ia64.c
index 90a7663910..0dde420095 100644
--- a/linux-2.6-xen-sparse/arch/ia64/xen/drivers/evtchn_ia64.c
+++ b/linux-2.6-xen-sparse/arch/ia64/xen/drivers/evtchn_ia64.c
@@ -4,7 +4,7 @@
 #include <linux/config.h>
 #include <linux/kernel.h>
 #include <asm/hw_irq.h>
-#include <asm-xen/evtchn.h>
+#include <xen/evtchn.h>
 
 #define MAX_EVTCHN 1024
 
diff --git a/linux-2.6-xen-sparse/arch/ia64/xen/xenentry.S b/linux-2.6-xen-sparse/arch/ia64/xen/xenentry.S
index 8d701f3284..0d1ded964a 100644
--- a/linux-2.6-xen-sparse/arch/ia64/xen/xenentry.S
+++ b/linux-2.6-xen-sparse/arch/ia64/xen/xenentry.S
@@ -14,7 +14,7 @@
 #include <asm/cache.h>
 #include <asm/errno.h>
 #include <asm/kregs.h>
-#include <asm/offsets.h>
+#include <asm/asm-offsets.h>
 #include <asm/pgtable.h>
 #include <asm/percpu.h>
 #include <asm/processor.h>
diff --git a/linux-2.6-xen-sparse/arch/ia64/xen/xenivt.S b/linux-2.6-xen-sparse/arch/ia64/xen/xenivt.S
index 021050f441..d53b52ab37 100644
--- a/linux-2.6-xen-sparse/arch/ia64/xen/xenivt.S
+++ b/linux-2.6-xen-sparse/arch/ia64/xen/xenivt.S
@@ -35,7 +35,7 @@
 #include <asm/break.h>
 #include <asm/ia32.h>
 #include <asm/kregs.h>
-#include <asm/offsets.h>
+#include <asm/asm-offsets.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>