Merge tp1.ruhr-uni-bochum.de:/home/kai/kernel/v2.5/linus-2.5.vm

into tp1.ruhr-uni-bochum.de:/home/kai/kernel/v2.5/linux-2.5.make

arch/i386/kernel/i387.c

@@ -31,13 +31,21 @@
  * value at reset if we support XMM instructions and then
  * remeber the current task has used the FPU.
  */
-void init_fpu(void)
+void init_fpu(struct task_struct *tsk)
 {
-	__asm__("fninit");
-	if ( cpu_has_xmm )
-		load_mxcsr(0x1f80);
-		
-	current->used_math = 1;
+	if (cpu_has_fxsr) {
+		memset(&tsk->thread.i387.fxsave, 0, sizeof(struct i387_fxsave_struct));
+		tsk->thread.i387.fxsave.cwd = 0x37f;
+		if (cpu_has_xmm)
+			tsk->thread.i387.fxsave.mxcsr = 0x1f80;
+	} else {
+		memset(&tsk->thread.i387.fsave, 0, sizeof(struct i387_fsave_struct));
+		tsk->thread.i387.fsave.cwd = 0xffff037f;
+		tsk->thread.i387.fsave.swd = 0xffff0000;
+		tsk->thread.i387.fsave.twd = 0xffffffff;
+		tsk->thread.i387.fsave.fos = 0xffff0000;
+	}
+	tsk->used_math = 1;
 }
 
 /*

arch/i386/kernel/traps.c

@@ -757,13 +757,12 @@ asmlinkage void do_spurious_interrupt_bug(struct pt_regs * regs,
  */
 asmlinkage void math_state_restore(struct pt_regs regs)
 {
+	struct task_struct *tsk = current;
 	clts();		/* Allow maths ops (or we recurse) */
 
-	if (current->used_math) {
-		restore_fpu(current);
-	} else {
-		init_fpu();
-	}
+	if (!tsk->used_math)
+		init_fpu(tsk);
+	restore_fpu(tsk);
 	set_thread_flag(TIF_USEDFPU);	/* So we fnsave on switch_to() */
 }
 

arch/x86_64/Config.help

@@ -396,33 +396,31 @@ CONFIG_PM
   sending the processor to sleep and saving power.
 
 CONFIG_ACPI
-  ACPI/OSPM support for Linux is currently under development. As such,
-  this support is preliminary and EXPERIMENTAL.  Configuring ACPI
-  support enables kernel interfaces that allow higher level software
-  (OSPM) to manipulate ACPI defined hardware and software interfaces,
-  including the evaluation of ACPI control methods.  If unsure, choose
-  N here.  Note, this option will enlarge your kernel by about 120K.
-
-  This support requires an ACPI compliant platform (hardware/firmware).
-  If both ACPI and Advanced Power Management (APM) support are
-  configured, whichever is loaded first shall be used.
-
-  This code DOES NOT currently provide a complete OSPM implementation
-  -- it has not yet reached APM's level of functionality.  When fully
-  implemented, Linux ACPI/OSPM will provide a more robust functional
-  replacement for legacy configuration and power management
-  interfaces, including the Plug-and-Play BIOS specification (PnP
-  BIOS), the Multi-Processor Specification (MPS), and the Advanced
-  Power Management specification (APM).
-
-  Linux support for ACPI/OSPM is based on Intel Corporation's ACPI
-  Component Architecture (ACPI CA). The latest ACPI CA source code,
-  documentation, debug builds, and implementation status information
-  can be downloaded from:
-  <http://developer.intel.com/technology/iapc/acpi/downloads.htm>.
-
-  The ACPI Sourceforge project may also be of interest:
-  <http://sf.net/projects/acpi/>
+  Advanced Configuration and Power Interface (ACPI) support for 
+  Linux requires an ACPI compliant platform (hardware/firmware),
+  and assumes the presence of OS-directed configuration and power
+  management (OSPM) software. 
+
+  Linux ACPI provides a robust functional replacement for several 
+  legacy configuration and power management intefaces, including 
+  the Plug-and-Play BIOS specification (PnP BIOS), the 
+  MultiProcessor Specification (MPS), and the Advanced Power 
+  Management (APM) specification.  If both ACPI and APM support 
+  are configured, whichever is loaded first shall be used.
+  
+  The ACPI SourceForge project contains the latest source code, 
+  documentation, tools, mailing list subscription, and other 
+  information.  This project is available at:
+    <http://sourceforge.net/projects/acpi>
+
+  Linux support for ACPI is based on Intel Corporation's ACPI
+  Component Architecture (ACPI CA).  For more information see:
+    <http://developer.intel.com/technology/iapc/acpi>
+
+  ACPI is an open industry specification co-developed by Compaq, 
+  Intel, Microsoft, Phoenix, and Toshiba.  The specification is 
+  available at:
+    <http://www.acpi.info>
 
 CONFIG_X86_MSR
   This device gives privileged processes access to the x86
@@ -437,34 +435,6 @@ CONFIG_X86_CPUID
   with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to
   /dev/cpu/31/cpuid.
 
-CONFIG_SOUND
-  If you have a sound card in your computer, i.e. if it can say more
-  than an occasional beep, say Y.  Be sure to have all the information
-  about your sound card and its configuration down (I/O port,
-  interrupt and DMA channel), because you will be asked for it.
-
-  You want to read the Sound-HOWTO, available from
-  <http://www.linuxdoc.org/docs.html#howto>. General information about
-  the modular sound system is contained in the files
-  <file:Documentation/sound/Introduction>.  The file
-  <file:Documentation/sound/README.OSS> contains some slightly
-  outdated but still useful information as well.
-
-  If you have a PnP sound card and you want to configure it at boot
-  time using the ISA PnP tools (read
-  <http://www.roestock.demon.co.uk/isapnptools/>), then you need to
-  compile the sound card support as a module ( = code which can be
-  inserted in and removed from the running kernel whenever you want)
-  and load that module after the PnP configuration is finished.  To do
-  this, say M here and read <file:Documentation/modules.txt> as well
-  as <file:Documentation/sound/README.modules>; the module will be
-  called soundcore.o.
-
-  I'm told that even without a sound card, you can make your computer
-  say more than an occasional beep, by programming the PC speaker.
-  Kernel patches and supporting utilities to do that are in the pcsp
-  package, available at <ftp://ftp.infradead.org/pub/pcsp/>.
-
 CONFIG_PREEMPT
   This option reduces the latency of the kernel when reacting to
   real-time or interactive events by allowing a low priority process to
@@ -529,3 +499,13 @@ CONFIG_EARLY_PRINTK
   klogd/syslogd or the X server.You should normally N here, unless
   you want to debug such a crash.
   
+CONFIG_X86_MCE_NONFATAL
+  Enabling this feature starts a timer that triggers every 5 seconds which
+  will look at the machine check registers to see if anything happened.
+  Non-fatal problems automatically get corrected (but still logged).
+  Disable this if you don't want to see these messages.
+  Seeing the messages this option prints out may be indicative of dying hardware,
+  or out-of-spec (ie, overclocked) hardware.
+  This option only does something on hardware with Intel P6 style MCE.
+  (Pentium Pro and above, AMD Athlon/Duron)
+

arch/x86_64/Makefile

@@ -17,20 +17,19 @@
 # 20000913  Pavel Machek <pavel@suse.cz>
 #	    Converted for x86_64 architecture
 # 20010105  Andi Kleen, add IA32 compiler.
+#           ....and later removed it again....
 #
-# $Id: Makefile,v 1.28 2001/06/29 17:47:43 aj Exp $
-
+# $Id: Makefile,v 1.31 2002/03/22 15:56:07 ak Exp $
 
 #
-# boot system currently needs IA32 tools to link (to be fixed) 
+# early bootup linking needs 32bit. You can either use real 32bit tools
+# here or 64bit tools switch to 32bit mode.
 #
-# Change this to your i386 compiler/binutils
-IA32_PREFIX := /usr/bin/
-IA32_CC := $(IA32_PREFIX)gcc -O2 -fomit-frame-pointer -nostdinc -I $(HPATH)
-IA32_LD := $(IA32_PREFIX)ld
-IA32_AS := $(IA32_PREFIX)gcc -D__ASSEMBLY__ -traditional -c -nostdinc -I $(HPATH) 
-IA32_OBJCOPY := $(IA32_PREFIX)objcopy
-IA32_CPP := $(IA32_PREFIX)gcc -E
+IA32_CC := $(CROSS_COMPILE)gcc -m32 -O2 -fomit-frame-pointer -nostdinc -I $(HPATH)
+IA32_LD := $(CROSS_COMPILE)ld -m elf_i386
+IA32_AS := $(CROSS_COMPILE)gcc -m32 -Wa,--32 -D__ASSEMBLY__ -traditional -c -nostdinc -I $(HPATH) 
+IA32_OBJCOPY := $(CROSS_COMPILE)objcopy
+IA32_CPP := $(CROSS_COMPILE)gcc -m32 -E
 export IA32_CC IA32_LD IA32_AS IA32_OBJCOPY IA32_CPP
 
 
@@ -39,16 +38,14 @@ OBJCOPY=$(CROSS_COMPILE)objcopy -O binary -R .note -R .comment -S
 LDFLAGS=-e stext
 LINKFLAGS =-T $(TOPDIR)/arch/x86_64/vmlinux.lds $(LDFLAGS)
 
-CFLAGS += $(shell if $(CC) -mno-red-zone -S -o /dev/null -xc /dev/null >/dev/null 2>&1; then echo "-mno-red-zone"; fi ) 
+CFLAGS += -mno-red-zone
 CFLAGS += -mcmodel=kernel
 CFLAGS += -pipe
-# generates worse code, but makes the assembly much more readable:
 CFLAGS += -fno-reorder-blocks	
-# work around early gcc 3.1 bugs. Later snapshots should this already fixed.
+# needed for later gcc 3.1
+CFLAGS += -finline-limit=2000
+# needed for earlier gcc 3.1
 CFLAGS += -fno-strength-reduce
-# make sure all inline functions are inlined
-CFLAGS += -finline-limit=3000
-
 #CFLAGS += -g
 
 # prevent gcc from keeping the stack 16 byte aligned (FIXME)
@@ -61,8 +58,6 @@ CORE_FILES := arch/x86_64/kernel/kernel.o $(CORE_FILES)
 CORE_FILES +=  arch/x86_64/mm/mm.o
 LIBS := $(TOPDIR)/arch/x86_64/lib/lib.a $(LIBS)
 
-CLEAN_FILES += include/asm-x86_64/offset.h
-
 ifdef CONFIG_IA32_EMULATION
 SUBDIRS += arch/x86_64/ia32
 CORE_FILES += arch/x86_64/ia32/ia32.o
@@ -88,14 +83,14 @@ MAKEBOOT = $(MAKE) -C arch/$(ARCH)/boot
 
 vmlinux: arch/x86_64/vmlinux.lds
 
-checkoffset: FORCE
-	make -C arch/$(ARCH)/tools $(TOPDIR)/include/asm-x86_64/offset.h
-
 FORCE: ;
 
 .PHONY: zImage bzImage compressed zlilo bzlilo zdisk bzdisk install \
 		clean archclean archmrproper archdep checkoffset
 
+checkoffset: FORCE
+	make -C arch/$(ARCH)/tools $(TOPDIR)/include/asm-x86_64/offset.h
+
 bzImage: checkoffset vmlinux
 	@$(MAKEBOOT) bzImage
 
@@ -104,12 +99,10 @@ bzImage-padded: checkoffset vmlinux
 
 tmp:
 	@$(MAKEBOOT) BOOTIMAGE=bzImage zlilo
+
 bzlilo: checkoffset vmlinux
 	@$(MAKEBOOT) BOOTIMAGE=bzImage zlilo
 
-zdisk: checkoffset vmlinux
-	@$(MAKEBOOT) BOOTIMAGE=zImage zdisk
-
 bzdisk: checkoffset vmlinux
 	@$(MAKEBOOT) BOOTIMAGE=bzImage zdisk
 
@@ -118,7 +111,7 @@ install: checkoffset vmlinux
 
 archclean:
 	@$(MAKEBOOT) clean
-	$(MAKE) -C $(TOPDIR)/arch/x86_64/tools clean
+	@$(MAKE) -C $(TOPDIR)/arch/x86_64/tools clean
 
 archmrproper:
 	rm -f $(TOPDIR)/arch/x86_64/tools/offset.h

arch/x86_64/boot/setup.S

@@ -435,36 +435,7 @@ no_disk1:
 	rep
 	stosb
 is_disk1:
-# check for Micro Channel (MCA) bus
-	movw	%cs, %ax			# aka SETUPSEG
-	subw	$DELTA_INITSEG, %ax		# aka INITSEG
-	movw	%ax, %ds
-	xorw	%ax, %ax
-	movw	%ax, (0xa0)			# set table length to 0
-	movb	$0xc0, %ah
-	stc
-	int	$0x15				# moves feature table to es:bx
-	jc	no_mca
 
-	pushw	%ds
-	movw	%es, %ax
-	movw	%ax, %ds
-	movw	%cs, %ax			# aka SETUPSEG
-	subw	$DELTA_INITSEG, %ax		# aka INITSEG
-	movw	%ax, %es
-	movw	%bx, %si
-	movw	$0xa0, %di
-	movw	(%si), %cx
-	addw	$2, %cx				# table length is a short
-	cmpw	$0x10, %cx
-	jc	sysdesc_ok
-
-	movw	$0x10, %cx			# we keep only first 16 bytes
-sysdesc_ok:
-	rep
-	movsb
-	popw	%ds
-no_mca:
 # Check for PS/2 pointing device
 	movw	%cs, %ax			# aka SETUPSEG
 	subw	$DELTA_INITSEG, %ax		# aka INITSEG
@@ -477,71 +448,11 @@ no_mca:
 	movw	$0xAA, (0x1ff)			# device present
 no_psmouse:
 
-#if defined(CONFIG_APM) || defined(CONFIG_APM_MODULE)
-# Then check for an APM BIOS...
-						# %ds points to the bootsector
-	movw	$0, 0x40			# version = 0 means no APM BIOS
-	movw	$0x05300, %ax			# APM BIOS installation check
-	xorw	%bx, %bx
-	int	$0x15
-	jc	done_apm_bios			# Nope, no APM BIOS
-	
-	cmpw	$0x0504d, %bx			# Check for "PM" signature
-	jne	done_apm_bios			# No signature, no APM BIOS
-
-	andw	$0x02, %cx			# Is 32 bit supported?
-	je	done_apm_bios			# No 32-bit, no (good) APM BIOS
-
-	movw	$0x05304, %ax			# Disconnect first just in case
-	xorw	%bx, %bx
-	int	$0x15				# ignore return code
-	movw	$0x05303, %ax			# 32 bit connect
-	xorl	%ebx, %ebx
-	xorw	%cx, %cx			# paranoia :-)
-	xorw	%dx, %dx			#   ...
-	xorl	%esi, %esi			#   ...
-	xorw	%di, %di			#   ...
-	int	$0x15
-	jc	no_32_apm_bios			# Ack, error. 
-
-	movw	%ax,  (66)			# BIOS code segment
-	movl	%ebx, (68)			# BIOS entry point offset
-	movw	%cx,  (72)			# BIOS 16 bit code segment
-	movw	%dx,  (74)			# BIOS data segment
-	movl	%esi, (78)			# BIOS code segment lengths
-	movw	%di,  (82)			# BIOS data segment length
-# Redo the installation check as the 32 bit connect
-# modifies the flags returned on some BIOSs
-	movw	$0x05300, %ax			# APM BIOS installation check
-	xorw	%bx, %bx
-	xorw	%cx, %cx			# paranoia
-	int	$0x15
-	jc	apm_disconnect			# error -> shouldn't happen
-
-	cmpw	$0x0504d, %bx			# check for "PM" signature
-	jne	apm_disconnect			# no sig -> shouldn't happen
-
-	movw	%ax, (64)			# record the APM BIOS version
-	movw	%cx, (76)			# and flags
-	jmp	done_apm_bios
-
-apm_disconnect:					# Tidy up
-	movw	$0x05304, %ax			# Disconnect
-	xorw	%bx, %bx
-	int	$0x15				# ignore return code
-
-	jmp	done_apm_bios
-
-no_32_apm_bios:
-	andw	$0xfffd, (76)			# remove 32 bit support bit
-done_apm_bios:
-#endif
-
 # Now we want to move to protected mode ...
 	cmpw	$0, %cs:realmode_swtch
 	jz	rmodeswtch_normal
 
-	lcall	*%cs:realmode_swtch
+	lcall	%cs:realmode_swtch
 
 	jmp	rmodeswtch_end
 

arch/x86_64/boot/video.S

@@ -66,7 +66,6 @@
 #define VIDEO_80x30 0x0f05
 #define VIDEO_80x34 0x0f06
 #define VIDEO_80x60 0x0f07
-#define VIDEO_GFX_HACK 0x0f08
 #define VIDEO_LAST_SPECIAL 0x0f09
 
 /* Video modes given by resolution */
@@ -741,15 +740,7 @@ set_80x60:
 	movw	$0x503c, force_size
 	jmp	setvde
 
-# Special hack for ThinkPad graphics
 set_gfx:
-#ifdef CONFIG_VIDEO_GFX_HACK
-	movw	$VIDEO_GFX_BIOS_AX, %ax
-	movw	$VIDEO_GFX_BIOS_BX, %bx
-	int	$0x10
-	movw	$VIDEO_GFX_DUMMY_RESOLUTION, force_size
-	stc
-#endif
 	ret
 
 #ifdef CONFIG_VIDEO_RETAIN
@@ -974,10 +965,6 @@ vga_modes:
 	.word	0x5022				# 80x34
 	.word	VIDEO_80x60
 	.word	0x503c				# 80x60
-#ifdef CONFIG_VIDEO_GFX_HACK
-	.word	VIDEO_GFX_HACK
-	.word	VIDEO_GFX_DUMMY_RESOLUTION
-#endif
 
 vga_modes_end:
 # Detect VESA modes.

arch/x86_64/config.in

@@ -11,16 +11,16 @@ define_bool CONFIG_ISA y
 define_bool CONFIG_SBUS n
 
 define_bool CONFIG_UID16 y
-define_bool CONFIG_RWSEM_GENERIC_SPINLOCK n
-define_bool CONFIG_RWSEM_XCHGADD_ALGORITHM y
-
+define_bool CONFIG_RWSEM_GENERIC_SPINLOCK y
+define_bool CONFIG_RWSEM_XCHGADD_ALGORITHM n
+define_bool CONFIG_X86_CMPXCHG y
 
 source init/Config.in
 
 mainmenu_option next_comment
 comment 'Processor type and features'
 choice 'Processor family' \
-	"Clawhammer			CONFIG_MK8" Clawhammer
+	"AMD-Hammer			CONFIG_MK8" CONFIG_MK8
 	
 #
 # Define implied options from the CPU selection here
@@ -29,7 +29,6 @@ define_int CONFIG_X86_L1_CACHE_BYTES 64
 define_int CONFIG_X86_L1_CACHE_SHIFT 6
 define_bool CONFIG_X86_TSC y
 define_bool CONFIG_X86_GOOD_APIC y
-define_bool CONFIG_X86_CMPXCHG y
 
 tristate '/dev/cpu/*/msr - Model-specific register support' CONFIG_X86_MSR
 tristate '/dev/cpu/*/cpuid - CPU information support' CONFIG_X86_CPUID
@@ -37,32 +36,31 @@ tristate '/dev/cpu/*/cpuid - CPU information support' CONFIG_X86_CPUID
 define_bool CONFIG_MATH_EMULATION n
 define_bool CONFIG_MCA n
 define_bool CONFIG_EISA n
+define_bool CONFIG_X86_IO_APIC y
+define_bool CONFIG_X86_LOCAL_APIC y
 
-bool 'MTRR (Memory Type Range Register) support' CONFIG_MTRR
+#currently broken:
+#bool 'MTRR (Memory Type Range Register) support' CONFIG_MTRR
 bool 'Symmetric multi-processing support' CONFIG_SMP
 bool 'Preemptible Kernel' CONFIG_PREEMPT
-# currently doesn't boot without hacks. probably simulator bug.
-#if [ "$CONFIG_SMP" != "y" ]; then
-#   bool 'APIC and IO-APIC support on uniprocessors' CONFIG_X86_UP_IOAPIC
-#    if [ "$CONFIG_X86_UP_IOAPIC" = "y" ]; then
-#       define_bool CONFIG_X86_IO_APIC y
-#       define_bool CONFIG_X86_LOCAL_APIC y
-#    fi
-#fi
 if [ "$CONFIG_SMP" = "y" -a "$CONFIG_X86_CMPXCHG" = "y" ]; then
     define_bool CONFIG_HAVE_DEC_LOCK y
 fi
+
+define_bool CONFIG_X86_MCE y
+bool 'Check for non-fatal machine check errors' CONFIG_X86_MCE_NONFATAL $CONFIG_X86_MCE
+
 endmenu
 
 mainmenu_option next_comment
+
 comment 'General options'
 
-if [ "$CONFIG_SMP" = "y" ]; then
-   define_bool CONFIG_X86_IO_APIC y
-   define_bool CONFIG_X86_LOCAL_APIC y
-fi
+source drivers/acpi/Config.in
+
 bool 'PCI support' CONFIG_PCI
 if [ "$CONFIG_PCI" = "y" ]; then
+# x86-64 doesn't support PCI BIOS access from long mode so always go direct. 
    define_bool CONFIG_PCI_DIRECT y 
 fi
 
@@ -80,22 +78,14 @@ fi
 if [ "$CONFIG_PROC_FS" = "y" ]; then
    define_bool CONFIG_KCORE_ELF y
 fi
-# We probably are not going to support a.out, are we? Or should we support a.out in i386 compatibility mode?
-		#tristate 'Kernel support for a.out binaries' CONFIG_BINFMT_AOUT
-		tristate 'Kernel support for ELF binaries' CONFIG_BINFMT_ELF
+#tristate 'Kernel support for a.out binaries' CONFIG_BINFMT_AOUT
+tristate 'Kernel support for ELF binaries' CONFIG_BINFMT_ELF
 tristate 'Kernel support for MISC binaries' CONFIG_BINFMT_MISC
 
 bool 'Power Management support' CONFIG_PM
 
 bool 'IA32 Emulation' CONFIG_IA32_EMULATION
 
-if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then
-   dep_bool '  ACPI support' CONFIG_ACPI $CONFIG_PM
-   if [ "$CONFIG_ACPI" != "n" ]; then
-      source drivers/acpi/Config.in
-   fi
-fi
-
 endmenu
 
 source drivers/mtd/Config.in
@@ -186,10 +176,6 @@ endmenu
 source drivers/input/Config.in
 source drivers/char/Config.in
 
-if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then
-   source net/bluetooth/Config.in
-fi
-
 source drivers/misc/Config.in
 
 source drivers/media/Config.in
@@ -219,6 +205,10 @@ endmenu
 
 source drivers/usb/Config.in
 
+if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then
+   source net/bluetooth/Config.in
+fi
+
 mainmenu_option next_comment
 comment 'Kernel hacking'
 
@@ -228,13 +218,13 @@ if [ "$CONFIG_DEBUG_KERNEL" != "n" ]; then
 #   bool '  Memory mapped I/O debugging' CONFIG_DEBUG_IOVIRT
    bool '  Magic SysRq key' CONFIG_MAGIC_SYSRQ
    bool '  Spinlock debugging' CONFIG_DEBUG_SPINLOCK
-#   bool '  Early printk' CONFIG_EARLY_PRINTK
+   bool '  Early printk' CONFIG_EARLY_PRINTK
    bool '  Additional run-time checks' CONFIG_CHECKING
-fi
-bool 'Simnow environment (disables time-consuming things)' CONFIG_SIMNOW
+   bool '  Debug __init statements' CONFIG_INIT_DEBUG
 #if [ "$CONFIG_SERIAL_CONSOLE" = "y" ]; then
 #  bool 'Early serial console (ttyS0)' CONFIG_EARLY_SERIAL_CONSOLE
 #fi
+fi
 endmenu
 
 source lib/Config.in

arch/x86_64/defconfig

@@ -6,8 +6,9 @@ CONFIG_X86=y
 CONFIG_ISA=y
 # CONFIG_SBUS is not set
 CONFIG_UID16=y
-# CONFIG_RWSEM_GENERIC_SPINLOCK is not set
-CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
+# CONFIG_RWSEM_XCHGADD_ALGORITHM is not set
+CONFIG_X86_CMPXCHG=y
 
 #
 # Code maturity level options
@@ -37,19 +38,27 @@ CONFIG_X86_L1_CACHE_BYTES=64
 CONFIG_X86_L1_CACHE_SHIFT=6
 CONFIG_X86_TSC=y
 CONFIG_X86_GOOD_APIC=y
-CONFIG_X86_CMPXCHG=y
 CONFIG_X86_MSR=y
 CONFIG_X86_CPUID=y
 # CONFIG_MATH_EMULATION is not set
 # CONFIG_MCA is not set
 # CONFIG_EISA is not set
-CONFIG_MTRR=y
-# CONFIG_SMP is not set
+CONFIG_X86_IO_APIC=y
+CONFIG_X86_LOCAL_APIC=y
+CONFIG_SMP=y
 # CONFIG_PREEMPT is not set
+CONFIG_HAVE_DEC_LOCK=y
+CONFIG_X86_MCE=y
+# CONFIG_X86_MCE_NONFATAL is not set
 
 #
 # General options
 #
+
+#
+# ACPI Support
+#
+# CONFIG_ACPI is not set
 CONFIG_PCI=y
 CONFIG_PCI_DIRECT=y
 # CONFIG_PCI_NAMES is not set
@@ -60,7 +69,6 @@ CONFIG_BINFMT_ELF=y
 # CONFIG_BINFMT_MISC is not set
 CONFIG_PM=y
 CONFIG_IA32_EMULATION=y
-# CONFIG_ACPI is not set
 
 #
 # Memory Technology Devices (MTD)
@@ -162,7 +170,7 @@ CONFIG_INET=y
 CONFIG_IDE=y
 
 #
-# IDE, ATA and ATAPI Block devices
+# ATA and ATAPI Block devices
 #
 CONFIG_BLK_DEV_IDE=y
 
@@ -172,7 +180,7 @@ CONFIG_BLK_DEV_IDE=y
 # CONFIG_BLK_DEV_HD_IDE is not set
 # CONFIG_BLK_DEV_HD is not set
 CONFIG_BLK_DEV_IDEDISK=y
-# CONFIG_IDEDISK_MULTI_MODE is not set
+CONFIG_IDEDISK_MULTI_MODE=y
 # CONFIG_IDEDISK_STROKE is not set
 # CONFIG_BLK_DEV_IDEDISK_VENDOR is not set
 # CONFIG_BLK_DEV_IDEDISK_FUJITSU is not set
@@ -184,23 +192,55 @@ CONFIG_BLK_DEV_IDEDISK=y
 # CONFIG_BLK_DEV_COMMERIAL is not set
 # CONFIG_BLK_DEV_TIVO is not set
 # CONFIG_BLK_DEV_IDECS is not set
-# CONFIG_BLK_DEV_IDECD is not set
+CONFIG_BLK_DEV_IDECD=y
 # CONFIG_BLK_DEV_IDETAPE is not set
 # CONFIG_BLK_DEV_IDEFLOPPY is not set
 # CONFIG_BLK_DEV_IDESCSI is not set
 
 #
-# IDE chipset support/bugfixes
+# IDE chipset support
 #
 # CONFIG_BLK_DEV_CMD640 is not set
 # CONFIG_BLK_DEV_CMD640_ENHANCED is not set
 # CONFIG_BLK_DEV_ISAPNP is not set
 # CONFIG_BLK_DEV_RZ1000 is not set
-# CONFIG_BLK_DEV_IDEPCI is not set
+CONFIG_BLK_DEV_IDEPCI=y
+# CONFIG_BLK_DEV_OFFBOARD is not set
+# CONFIG_IDEPCI_SHARE_IRQ is not set
+CONFIG_BLK_DEV_IDEDMA_PCI=y
+CONFIG_IDEDMA_PCI_AUTO=y
+# CONFIG_IDEDMA_ONLYDISK is not set
+CONFIG_BLK_DEV_IDEDMA=y
+# CONFIG_BLK_DEV_IDE_TCQ is not set
+# CONFIG_BLK_DEV_IDE_TCQ_DEFAULT is not set
+# CONFIG_IDEDMA_PCI_WIP is not set
+# CONFIG_IDEDMA_NEW_DRIVE_LISTINGS is not set
+# CONFIG_BLK_DEV_AEC62XX is not set
+# CONFIG_AEC62XX_TUNING is not set
+# CONFIG_BLK_DEV_ALI15X3 is not set
+# CONFIG_WDC_ALI15X3 is not set
+# CONFIG_BLK_DEV_AMD74XX 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 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
+# CONFIG_BLK_DEV_PDC202XX is not set
+# CONFIG_PDC202XX_BURST is not set
+# CONFIG_PDC202XX_FORCE is not set
+# CONFIG_BLK_DEV_SVWKS is not set
+# CONFIG_BLK_DEV_SIS5513 is not set
+# CONFIG_BLK_DEV_TRM290 is not set
+# CONFIG_BLK_DEV_VIA82CXXX is not set
 # CONFIG_IDE_CHIPSETS is not set
-# CONFIG_IDEDMA_AUTO is not set
+# CONFIG_IDEDMA_IVB is not set
+CONFIG_IDEDMA_AUTO=y
 # CONFIG_DMA_NONPCI is not set
-# CONFIG_BLK_DEV_IDE_MODES is not set
 # CONFIG_BLK_DEV_ATARAID is not set
 # CONFIG_BLK_DEV_ATARAID_PDC is not set
 # CONFIG_BLK_DEV_ATARAID_HPT is not set
@@ -315,11 +355,6 @@ CONFIG_PSMOUSE=y
 # CONFIG_DRM is not set
 # CONFIG_MWAVE is not set
 
-#
-# Bluetooth support
-#
-# CONFIG_BLUEZ is not set
-
 #
 # Misc devices
 #
@@ -359,6 +394,9 @@ CONFIG_RAMFS=y
 # CONFIG_ISO9660_FS is not set
 # CONFIG_JOLIET is not set
 # CONFIG_ZISOFS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_JFS_DEBUG is not set
+# CONFIG_JFS_STATISTICS is not set
 # CONFIG_MINIX_FS is not set
 # CONFIG_VXFS_FS is not set
 # CONFIG_NTFS_FS is not set
@@ -389,6 +427,7 @@ CONFIG_EXT2_FS=y
 # CONFIG_ROOT_NFS is not set
 # CONFIG_NFSD is not set
 # CONFIG_NFSD_V3 is not set
+# CONFIG_NFSD_TCP is not set
 # CONFIG_SUNRPC is not set
 # CONFIG_LOCKD is not set
 # CONFIG_SMB_FS is not set
@@ -434,110 +473,9 @@ CONFIG_VGA_CONSOLE=y
 # CONFIG_USB is not set
 
 #
-# USB Host Controller Drivers
-#
-# CONFIG_USB_EHCI_HCD is not set
-# CONFIG_USB_OHCI_HCD is not set
-# CONFIG_USB_UHCI is not set
-# CONFIG_USB_UHCI_ALT is not set
-# CONFIG_USB_OHCI is not set
-
-#
-# USB Device Class drivers
-#
-# CONFIG_USB_AUDIO is not set
-# CONFIG_USB_BLUETOOTH is not set
-
-#
-#   SCSI support is needed for USB Storage
-#
-# CONFIG_USB_STORAGE is not set
-# CONFIG_USB_STORAGE_DEBUG is not set
-# CONFIG_USB_STORAGE_DATAFAB is not set
-# CONFIG_USB_STORAGE_FREECOM is not set
-# CONFIG_USB_STORAGE_ISD200 is not set
-# CONFIG_USB_STORAGE_DPCM is not set
-# 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)
-#
-
-#
-#   Input core support is needed for USB HID
-#
-
-#
-# USB Imaging devices
-#
-# CONFIG_USB_DC2XX is not set
-# CONFIG_USB_MDC800 is not set
-# CONFIG_USB_SCANNER is not set
-# CONFIG_USB_MICROTEK is not set
-# CONFIG_USB_HPUSBSCSI is not set
-
-#
-# USB Multimedia devices
-#
-
-#
-#   Video4Linux support is needed for USB Multimedia device support
-#
-
-#
-# 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_USBNET is not set
-
-#
-# USB port drivers
-#
-# CONFIG_USB_USS720 is not set
-
-#
-# USB Serial Converter support
-#
-# CONFIG_USB_SERIAL is not set
-# CONFIG_USB_SERIAL_GENERIC is not set
-# CONFIG_USB_SERIAL_BELKIN is not set
-# CONFIG_USB_SERIAL_WHITEHEAT is not set
-# CONFIG_USB_SERIAL_DIGI_ACCELEPORT is not set
-# CONFIG_USB_SERIAL_EMPEG is not set
-# CONFIG_USB_SERIAL_FTDI_SIO is not set
-# CONFIG_USB_SERIAL_VISOR is not set
-# CONFIG_USB_SERIAL_IPAQ is not set
-# CONFIG_USB_SERIAL_IR is not set
-# CONFIG_USB_SERIAL_EDGEPORT is not set
-# CONFIG_USB_SERIAL_KEYSPAN_PDA is not set
-# CONFIG_USB_SERIAL_KEYSPAN is not set
-# CONFIG_USB_SERIAL_KEYSPAN_USA28 is not set
-# CONFIG_USB_SERIAL_KEYSPAN_USA28X is not set
-# CONFIG_USB_SERIAL_KEYSPAN_USA28XA is not set
-# CONFIG_USB_SERIAL_KEYSPAN_USA28XB is not set
-# CONFIG_USB_SERIAL_KEYSPAN_USA19 is not set
-# 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_PL2303 is not set
-# CONFIG_USB_SERIAL_CYBERJACK is not set
-# CONFIG_USB_SERIAL_XIRCOM is not set
-# CONFIG_USB_SERIAL_OMNINET is not set
-
-#
-# USB Miscellaneous drivers
+# Bluetooth support
 #
-# CONFIG_USB_RIO500 is not set
-# CONFIG_USB_AUERSWALD is not set
+# CONFIG_BLUEZ is not set
 
 #
 # Kernel hacking
@@ -546,8 +484,9 @@ CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SLAB is not set
 # CONFIG_MAGIC_SYSRQ is not set
 # CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_EARLY_PRINTK is not set
 # CONFIG_CHECKING is not set
-CONFIG_SIMNOW=y
+# CONFIG_INIT_DEBUG is not set
 
 #
 # Library routines

arch/x86_64/ia32/Makefile

@@ -7,11 +7,13 @@
 .S.o:
 	$(CC) $(AFLAGS) -c -o $*.o $<
 
+export-objs := ia32_ioctl.o	
+
 all: ia32.o
 
 O_TARGET := ia32.o
-obj-$(CONFIG_IA32_EMULATION)	 := ia32entry.o sys_ia32.o ia32_ioctl.o ia32_signal.o ia32_binfmt.o \
-	socket32.o ptrace32.o
+obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_ioctl.o ia32_signal.o \
+	ia32_binfmt.o fpu32.o socket32.o ptrace32.o
 
 clean::
 

arch/x86_64/ia32/fpu32.c

+/* 
+ * Copyright 2002 Andi Kleen, SuSE Labs.
+ * FXSAVE<->i387 conversion support. Based on code by Gareth Hughes.
+ * This is used for ptrace, signals and coredumps in 32bit emulation.
+ * $Id: fpu32.c,v 1.1 2002/03/21 14:16:32 ak Exp $
+ */ 
+
+#include <linux/sched.h>
+#include <asm/sigcontext32.h>
+#include <asm/processor.h>
+#include <asm/uaccess.h>
+#include <asm/i387.h>
+
+static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
+{
+	unsigned int tmp; /* to avoid 16 bit prefixes in the code */
+ 
+	/* Transform each pair of bits into 01 (valid) or 00 (empty) */
+        tmp = ~twd;
+        tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
+        /* and move the valid bits to the lower byte. */
+        tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
+        tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
+        tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
+        return tmp;
+}
+
+static inline unsigned long twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave)
+{
+	struct _fpxreg *st = NULL;
+	unsigned long twd = (unsigned long) fxsave->twd;
+	unsigned long tag;
+	unsigned long ret = 0xffff0000;
+	int i;
+
+#define FPREG_ADDR(f, n)	((char *)&(f)->st_space + (n) * 16);
+
+	for (i = 0 ; i < 8 ; i++) {
+		if (twd & 0x1) {
+			st = (struct _fpxreg *) FPREG_ADDR( fxsave, i );
+
+			switch (st->exponent & 0x7fff) {
+			case 0x7fff:
+				tag = 2;		/* Special */
+				break;
+			case 0x0000:
+				if ( !st->significand[0] &&
+				     !st->significand[1] &&
+				     !st->significand[2] &&
+				     !st->significand[3] ) {
+					tag = 1;	/* Zero */
+				} else {
+					tag = 2;	/* Special */
+				}
+				break;
+			default:
+				if (st->significand[3] & 0x8000) {
+					tag = 0;	/* Valid */
+				} else {
+					tag = 2;	/* Special */
+				}
+				break;
+			}
+		} else {
+			tag = 3;			/* Empty */
+		}
+		ret |= (tag << (2 * i));
+		twd = twd >> 1;
+	}
+	return ret;
+}
+
+
+static inline int convert_fxsr_from_user(struct i387_fxsave_struct *fxsave,
+					 struct _fpstate_ia32 *buf)
+{
+	struct _fpxreg *to;
+	struct _fpreg *from;
+	int i;
+	int err; 
+	__u32 v;
+
+	err = __get_user(fxsave->cwd, (u16 *)&buf->cw); 
+	err |= __get_user(fxsave->swd, (u16 *)&buf->sw);
+	err |= __get_user(fxsave->twd, (u16 *)&buf->tag);
+	fxsave->twd = twd_i387_to_fxsr(fxsave->twd);
+	err |= __get_user(fxsave->rip, &buf->ipoff); 
+	err |= __get_user(fxsave->rdp, &buf->dataoff); 
+	err |= __get_user(v, &buf->cssel); 
+	fxsave->fop = v >> 16;
+	if (err) 
+		return -1; 
+
+	to = (struct _fpxreg *)&fxsave->st_space[0];
+	from = &buf->_st[0];
+	for (i = 0 ; i < 8 ; i++, to++, from++) {
+		if (__copy_from_user(to, from, sizeof(*from)))
+			return -1;
+	}
+	return 0;
+}
+
+
+static inline int convert_fxsr_to_user(struct _fpstate_ia32 *buf,
+				       struct i387_fxsave_struct *fxsave,
+				       struct pt_regs *regs,
+				       struct task_struct *tsk)
+{
+	struct _fpreg *to;
+	struct _fpxreg *from;
+	int i;
+	u32 ds; 
+	int err; 
+
+	err = __put_user((unsigned long)fxsave->cwd | 0xffff0000, &buf->cw);
+	err |= __put_user((unsigned long)fxsave->swd | 0xffff0000, &buf->sw);
+	err |= __put_user((u32)fxsave->rip, &buf->ipoff); 
+	err |= __put_user((u32)(regs->cs | ((u32)fxsave->fop << 16)), 
+			  &buf->cssel); 
+	err |= __put_user((u32)twd_fxsr_to_i387(fxsave), &buf->tag); 
+	err |= __put_user((u32)fxsave->rdp, &buf->dataoff); 
+	if (tsk == current) 
+		asm("movl %%ds,%0 " : "=r" (ds)); 
+	else /* ptrace. task has stopped. */
+		ds = tsk->thread.ds;
+	err |= __put_user(ds, &buf->datasel); 
+	if (err) 
+		return -1; 
+
+	to = &buf->_st[0];
+	from = (struct _fpxreg *) &fxsave->st_space[0];
+	for ( i = 0 ; i < 8 ; i++, to++, from++ ) {
+		if (__copy_to_user(to, from, sizeof(*to)))
+			return -1;
+	}
+	return 0;
+}
+
+int restore_i387_ia32(struct task_struct *tsk, struct _fpstate_ia32 *buf, int fsave) 
+{ 
+	clear_fpu(tsk);
+	if (!fsave) { 
+		if (__copy_from_user(&tsk->thread.i387.fxsave, 
+				     &buf->_fxsr_env[0],
+				     sizeof(struct i387_fxsave_struct)))
+			return -1;
+	} 
+	tsk->thread.i387.fxsave.mxcsr &= 0xffbf;
+	return convert_fxsr_from_user(&tsk->thread.i387.fxsave, buf);
+}  
+
+int save_i387_ia32(struct task_struct *tsk, 
+		   struct _fpstate_ia32 *buf, 
+		   struct pt_regs *regs,
+		   int fsave)
+{
+	int err = 0;
+
+	if (!tsk->used_math) 
+		return 0;
+	tsk->used_math = 0; 
+	unlazy_fpu(tsk);
+	if (convert_fxsr_to_user(buf, &tsk->thread.i387.fxsave, regs, tsk))
+		return -1;
+	err |= __put_user(tsk->thread.i387.fxsave.swd, &buf->status);
+	if (fsave) 
+		return err ? -1 : 1; 	
+	err |= __put_user(X86_FXSR_MAGIC, &buf->magic);
+	err |= __copy_to_user(&buf->_fxsr_env[0], &tsk->thread.i387.fxsave,
+			      sizeof(struct i387_fxsave_struct));
+	return err ? -1 : 1;
+}

arch/x86_64/ia32/ia32_binfmt.c

 /* 
- * Written 2000 by Andi Kleen. 
+ * Written 2000,2002 by Andi Kleen. 
  * 
  * Losely based on the sparc64 and IA64 32bit emulation loaders.
+ * This tricks binfmt_elf.c into loading 32bit binaries using lots 
+ * of ugly preprocessor tricks. Talk about very very poor man's inheritance.
  */ 
 #include <linux/types.h>
 #include <linux/config.h> 
 #include <linux/stddef.h>
 #include <linux/module.h>
 #include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/string.h>
 #include <asm/segment.h> 
 #include <asm/ptrace.h>
 #include <asm/processor.h>
+#include <asm/user32.h>
+#include <asm/sigcontext32.h>
+#include <asm/fpu32.h>
+#include <asm/i387.h>
 
 struct file;
 struct elf_phdr; 
@@ -28,19 +36,99 @@ struct elf_phdr;
 #define ELF_CLASS ELFCLASS32
 
 #define ELF_DATA	ELFDATA2LSB
-//#define USE_ELF_CORE_DUMP
+
+#define USE_ELF_CORE_DUMP 1
+
+/* Overwrite elfcore.h */ 
+#define _LINUX_ELFCORE_H 1
+typedef unsigned int elf_greg_t;
+
+#define ELF_NGREG (sizeof (struct user_regs_struct32) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+struct elf_siginfo
+{
+	int	si_signo;			/* signal number */
+	int	si_code;			/* extra code */
+	int	si_errno;			/* errno */
+};
+
+struct timeval32
+{
+    int tv_sec, tv_usec;
+};
+
+struct elf_prstatus
+{
+	struct elf_siginfo pr_info;	/* Info associated with signal */
+	short	pr_cursig;		/* Current signal */
+	unsigned int pr_sigpend;	/* Set of pending signals */
+	unsigned int pr_sighold;	/* Set of held signals */
+	pid_t	pr_pid;
+	pid_t	pr_ppid;
+	pid_t	pr_pgrp;
+	pid_t	pr_sid;
+	struct timeval32 pr_utime;	/* User time */
+	struct timeval32 pr_stime;	/* System time */
+	struct timeval32 pr_cutime;	/* Cumulative user time */
+	struct timeval32 pr_cstime;	/* Cumulative system time */
+	elf_gregset_t pr_reg;	/* GP registers */
+	int pr_fpvalid;		/* True if math co-processor being used.  */
+};
+
+#define ELF_PRARGSZ	(80)	/* Number of chars for args */
+
+struct elf_prpsinfo
+{
+	char	pr_state;	/* numeric process state */
+	char	pr_sname;	/* char for pr_state */
+	char	pr_zomb;	/* zombie */
+	char	pr_nice;	/* nice val */
+	unsigned int pr_flag;	/* flags */
+	__u16	pr_uid;
+	__u16	pr_gid;
+	pid_t	pr_pid, pr_ppid, pr_pgrp, pr_sid;
+	/* Lots missing */
+	char	pr_fname[16];	/* filename of executable */
+	char	pr_psargs[ELF_PRARGSZ];	/* initial part of arg list */
+};
+
+#define __STR(x) #x
+#define STR(x) __STR(x)
+
+#define _GET_SEG(x) \
+	({ __u32 seg; asm("movl %%" STR(x) ",%0" : "=r"(seg)); seg; })
+
+/* Assumes current==process to be dumped */
+#define ELF_CORE_COPY_REGS(pr_reg, regs)       		\
+	pr_reg[0] = regs->rbx;				\
+	pr_reg[1] = regs->rcx;				\
+	pr_reg[2] = regs->rdx;				\
+	pr_reg[3] = regs->rsi;				\
+	pr_reg[4] = regs->rdi;				\
+	pr_reg[5] = regs->rbp;				\
+	pr_reg[6] = regs->rax;				\
+	pr_reg[7] = _GET_SEG(ds);   			\
+	pr_reg[8] = _GET_SEG(es);			\
+	pr_reg[9] = _GET_SEG(fs);			\
+	pr_reg[10] = _GET_SEG(gs);			\
+	pr_reg[11] = regs->orig_rax;			\
+	pr_reg[12] = regs->rip;				\
+	pr_reg[13] = regs->cs;				\
+	pr_reg[14] = regs->eflags;			\
+	pr_reg[15] = regs->rsp;				\
+	pr_reg[16] = regs->ss;
+
+#define user user32
+
+#define dump_fpu dump_fpu_ia32
 
 #define __ASM_X86_64_ELF_H 1
 #include <asm/ia32.h>
 #include <linux/elf.h>
 
-typedef __u32  elf_greg_t;
-
-typedef elf_greg_t elf_gregset_t[8];
-
-/* FIXME -- wrong */
 typedef struct user_i387_ia32_struct elf_fpregset_t;
-typedef struct user_i387_struct elf_fpxregset_t;
+typedef struct user32_fxsr_struct elf_fpxregset_t;
 
 #undef elf_check_arch
 #define elf_check_arch(x) \
@@ -177,11 +265,35 @@ elf32_map (struct file *filep, unsigned long addr, struct elf_phdr *eppnt, int p
 	unsigned long map_addr;
 	struct task_struct *me = current; 
 
+	if (prot & PROT_READ) 
+		prot |= PROT_EXEC; 
+
 	down_write(&me->mm->mmap_sem);
 	map_addr = do_mmap(filep, ELF_PAGESTART(addr),
-			   eppnt->p_filesz + ELF_PAGEOFFSET(eppnt->p_vaddr), prot, type|MAP_32BIT,
+			   eppnt->p_filesz + ELF_PAGEOFFSET(eppnt->p_vaddr), prot, 
+			   type|MAP_32BIT,
 			   eppnt->p_offset - ELF_PAGEOFFSET(eppnt->p_vaddr));
 	up_write(&me->mm->mmap_sem);
 	return(map_addr);
 }
 
+int dump_fpu_ia32(struct pt_regs *regs, elf_fpregset_t *fp)
+{
+	struct _fpstate_ia32 *fpu = (void*)fp; 
+	struct task_struct *tsk = current;
+	mm_segment_t oldfs = get_fs();
+	int ret;
+
+	if (!tsk->used_math) 
+		return 0;
+	if (!(test_thread_flag(TIF_IA32)))
+		BUG(); 
+	unlazy_fpu(tsk);
+	set_fs(KERNEL_DS); 
+	ret = save_i387_ia32(current, fpu, regs, 1);
+	/* Correct for i386 bug. It puts the fop into the upper 16bits of 
+	   the tag word (like FXSAVE), not into the fcs*/ 
+	fpu->cssel |= fpu->tag & 0xffff0000; 
+	set_fs(oldfs); 
+	return ret; 
+}

arch/x86_64/ia32/ia32_ioctl.c

-/* $Id: ia32_ioctl.c,v 1.2 2001/07/05 06:28:42 ak Exp $
+/* $Id: ia32_ioctl.c,v 1.11 2002/04/18 14:36:37 ak Exp $
  * ioctl32.c: Conversion between 32bit and 64bit native ioctls.
  *
  * Copyright (C) 1997-2000  Jakub Jelinek  (jakub@redhat.com)
  * Copyright (C) 1998  Eddie C. Dost  (ecd@skynet.be)
- * Copyright (C) 2001  Andi Kleen, SuSE Labs 
+ * Copyright (C) 2001,2002  Andi Kleen, SuSE Labs 
  *
  * These routines maintain argument size conversion between 32bit and 64bit
  * ioctls.
@@ -51,6 +51,10 @@
 #include <linux/elevator.h>
 #include <linux/rtc.h>
 #include <linux/pci.h>
+#include <linux/rtc.h>
+#include <linux/module.h>
+#include <linux/serial.h>
+#include <linux/reiserfs_fs.h>
 #if defined(CONFIG_BLK_DEV_LVM) || defined(CONFIG_BLK_DEV_LVM_MODULE)
 /* Ugh. This header really is not clean */
 #define min min
@@ -2972,12 +2976,139 @@ static int ioc_settimeout(unsigned int fd, unsigned int cmd, unsigned long arg)
 	return rw_long(fd, AUTOFS_IOC_SETTIMEOUT, arg);
 }
 
+/* SuSE extension */ 
+#ifndef TIOCGDEV
+#define TIOCGDEV       _IOR('T',0x32, unsigned int)
+#endif
+static int tiocgdev(unsigned fd, unsigned cmd,  unsigned int *ptr) 
+{ 
+
+	struct file *file = fget(fd);
+	struct tty_struct *real_tty;
+
+	if (!fd)
+		return -EBADF;
+	if (file->f_op->ioctl != tty_ioctl)
+		return -EINVAL; 
+	real_tty = (struct tty_struct *)file->private_data;
+	if (!real_tty) 	
+		return -EINVAL; 
+	return put_user(kdev_t_to_nr(real_tty->device), ptr); 
+} 
+
+
+struct raw32_config_request 
+{
+	int	raw_minor;
+	__u64	block_major;
+	__u64	block_minor;
+} __attribute__((packed));
+
+static int raw_ioctl(unsigned fd, unsigned cmd,  void *ptr) 
+{ 
+	int ret;
+	switch (cmd) { 
+	case RAW_SETBIND:
+	case RAW_GETBIND: {
+		struct raw_config_request req; 
+		struct raw32_config_request *user_req = ptr;
+		mm_segment_t oldfs = get_fs(); 
+
+		if (get_user(req.raw_minor, &user_req->raw_minor) ||
+		    get_user(req.block_major, &user_req->block_major) ||
+		    get_user(req.block_minor, &user_req->block_minor))
+			return -EFAULT;
+		set_fs(KERNEL_DS); 
+		ret = sys_ioctl(fd,cmd,(unsigned long)&req); 
+		set_fs(oldfs); 
+		break;
+	}
+	default:
+		ret = sys_ioctl(fd,cmd,(unsigned long)ptr);
+		break;
+	} 
+	return ret; 		
+} 
+
+struct serial_struct32 {
+	int	type;
+	int	line;
+	unsigned int	port;
+	int	irq;
+	int	flags;
+	int	xmit_fifo_size;
+	int	custom_divisor;
+	int	baud_base;
+	unsigned short	close_delay;
+	char	io_type;
+	char	reserved_char[1];
+	int	hub6;
+	unsigned short	closing_wait; /* time to wait before closing */
+	unsigned short	closing_wait2; /* no longer used... */
+	__u32 iomem_base;
+	unsigned short	iomem_reg_shift;
+	unsigned int	port_high;
+	int	reserved[1];
+};
+
+static int serial_struct_ioctl(unsigned fd, unsigned cmd,  void *ptr) 
+{
+	typedef struct serial_struct SS;
+	struct serial_struct32 *ss32 = ptr; 
+	int err = 0;
+	struct serial_struct ss; 
+	mm_segment_t oldseg = get_fs(); 
+	set_fs(KERNEL_DS);
+	if (cmd == TIOCSSERIAL) { 
+		err = -EFAULT;
+		if (copy_from_user(&ss, ss32, sizeof(struct serial_struct32)))
+			goto out;
+		memmove(&ss.iomem_reg_shift, ((char*)&ss.iomem_base)+4, 
+			sizeof(SS)-offsetof(SS,iomem_reg_shift)); 
+		ss.iomem_base = (void *)((unsigned long)ss.iomem_base & 0xffffffff);
+	}
+	if (!err)
+		err = sys_ioctl(fd,cmd,(unsigned long)(&ss)); 
+	if (cmd == TIOCGSERIAL && err >= 0) { 
+		__u32 base;
+		if (__copy_to_user(ss32,&ss,offsetof(SS,iomem_base)) ||
+		    __copy_to_user(&ss32->iomem_reg_shift,
+				   &ss.iomem_reg_shift,
+				   sizeof(SS) - offsetof(SS, iomem_reg_shift)))
+			err = -EFAULT;
+		if (ss.iomem_base > (unsigned char *)0xffffffff)
+			base = -1; 
+		else
+			base = (unsigned long)ss.iomem_base;
+		err |= __put_user(base, &ss32->iomem_base); 		
+	} 
+ out:
+	set_fs(oldseg);
+	return err;	
+}
+
 struct ioctl_trans {
 	unsigned long cmd;
-	unsigned long handler;
+	int (*handler)(unsigned int, unsigned int, unsigned long, struct file * filp);
 	struct ioctl_trans *next;
 };
 
+/* generic function to change a single long put_user to arg to 32bit */
+static int arg2long(unsigned int fd, unsigned int cmd, unsigned long arg)
+{
+	int ret; 
+	unsigned long val = 0; 
+	mm_segment_t oldseg = get_fs();
+	set_fs(KERNEL_DS);
+	ret = sys_ioctl(fd, cmd, (unsigned long)&val);  
+	set_fs(oldseg); 
+	if (!ret || val) {
+		if (put_user((int)val, (unsigned int *)arg)) 
+			return -EFAULT; 
+	}
+	return ret; 
+} 
+
 #define REF_SYMBOL(handler) if (0) (void)handler;
 #define HANDLE_IOCTL2(cmd,handler) REF_SYMBOL(handler);  asm volatile(".quad %c0, " #handler ",0"::"i" (cmd)); 
 #define HANDLE_IOCTL(cmd,handler) HANDLE_IOCTL2(cmd,handler)
@@ -2986,7 +3117,7 @@ struct ioctl_trans {
 #define IOCTL_TABLE_END  asm volatile("\nioctl_end:"); }
 
 IOCTL_TABLE_START
-/* List here exlicitly which ioctl's are known to have
+/* List here explicitly which ioctl's are known to have
  * compatable types passed or none at all...
  */
 /* Big T */
@@ -3002,6 +3133,7 @@ COMPATIBLE_IOCTL(TCSETS)
 COMPATIBLE_IOCTL(TCSETSW)
 COMPATIBLE_IOCTL(TCSETSF)
 COMPATIBLE_IOCTL(TIOCLINUX)
+HANDLE_IOCTL(TIOCGDEV, tiocgdev)
 /* Little t */
 COMPATIBLE_IOCTL(TIOCGETD)
 COMPATIBLE_IOCTL(TIOCSETD)
@@ -3025,8 +3157,6 @@ COMPATIBLE_IOCTL(TIOCGPGRP)
 COMPATIBLE_IOCTL(TIOCSCTTY)
 COMPATIBLE_IOCTL(TIOCGPTN)
 COMPATIBLE_IOCTL(TIOCSPTLCK)
-COMPATIBLE_IOCTL(TIOCGSERIAL)
-COMPATIBLE_IOCTL(TIOCSSERIAL)
 COMPATIBLE_IOCTL(TIOCSERGETLSR)
 COMPATIBLE_IOCTL(FBIOGET_VSCREENINFO)
 COMPATIBLE_IOCTL(FBIOPUT_VSCREENINFO)
@@ -3082,6 +3212,8 @@ COMPATIBLE_IOCTL(BLKROSET)
 COMPATIBLE_IOCTL(BLKROGET)
 COMPATIBLE_IOCTL(BLKRRPART)
 COMPATIBLE_IOCTL(BLKFLSBUF)
+COMPATIBLE_IOCTL(BLKRASET)
+COMPATIBLE_IOCTL(BLKFRASET)
 COMPATIBLE_IOCTL(BLKSECTSET)
 COMPATIBLE_IOCTL(BLKSSZGET)
 
@@ -3203,7 +3335,7 @@ COMPATIBLE_IOCTL(RTC_RD_TIME)
 COMPATIBLE_IOCTL(RTC_SET_TIME)
 COMPATIBLE_IOCTL(RTC_WKALM_SET)
 COMPATIBLE_IOCTL(RTC_WKALM_RD)
-COMPATIBLE_IOCTL(RTC_IRQP_READ)
+HANDLE_IOCTL(RTC_IRQP_READ,arg2long)
 COMPATIBLE_IOCTL(RTC_IRQP_SET)
 COMPATIBLE_IOCTL(RTC_EPOCH_READ)
 COMPATIBLE_IOCTL(RTC_EPOCH_SET)
@@ -3479,9 +3611,6 @@ COMPATIBLE_IOCTL(DEVFSDIOC_GET_PROTO_REV)
 COMPATIBLE_IOCTL(DEVFSDIOC_SET_EVENT_MASK)
 COMPATIBLE_IOCTL(DEVFSDIOC_RELEASE_EVENT_QUEUE)
 COMPATIBLE_IOCTL(DEVFSDIOC_SET_DEBUG_MASK)
-/* Raw devices */
-COMPATIBLE_IOCTL(RAW_SETBIND)
-COMPATIBLE_IOCTL(RAW_GETBIND)
 /* SMB ioctls which do not need any translations */
 COMPATIBLE_IOCTL(SMB_IOC_NEWCONN)
 /* Little a */
@@ -3543,6 +3672,18 @@ COMPATIBLE_IOCTL(DRM_IOCTL_LOCK)
 COMPATIBLE_IOCTL(DRM_IOCTL_UNLOCK)
 COMPATIBLE_IOCTL(DRM_IOCTL_FINISH)
 #endif /* DRM */
+#ifdef CONFIG_AUTOFS_FS
+COMPATIBLE_IOCTL(AUTOFS_IOC_READY);
+COMPATIBLE_IOCTL(AUTOFS_IOC_FAIL);
+COMPATIBLE_IOCTL(AUTOFS_IOC_CATATONIC);
+COMPATIBLE_IOCTL(AUTOFS_IOC_PROTOVER);
+COMPATIBLE_IOCTL(AUTOFS_IOC_SETTIMEOUT);
+COMPATIBLE_IOCTL(AUTOFS_IOC_EXPIRE);
+#endif
+COMPATIBLE_IOCTL(REISERFS_IOC_UNPACK);
+/* serial driver */ 
+HANDLE_IOCTL(TIOCGSERIAL, serial_struct_ioctl);
+HANDLE_IOCTL(TIOCSSERIAL, serial_struct_ioctl);
 /* elevator */
 COMPATIBLE_IOCTL(BLKELVGET)
 COMPATIBLE_IOCTL(BLKELVSET)
@@ -3589,6 +3730,8 @@ HANDLE_IOCTL(SIOCSIFTXQLEN, dev_ifsioc)
 HANDLE_IOCTL(SIOCETHTOOL, ethtool_ioctl)
 HANDLE_IOCTL(SIOCADDRT, routing_ioctl)
 HANDLE_IOCTL(SIOCDELRT, routing_ioctl)
+/* Raw devices */
+HANDLE_IOCTL(RAW_SETBIND, raw_ioctl)
 /* Note SIOCRTMSG is no longer, so this is safe and * the user would have seen just an -EINVAL anyways. */
 HANDLE_IOCTL(SIOCRTMSG, ret_einval)
 HANDLE_IOCTL(SIOCGSTAMP, do_siocgstamp)
@@ -3751,14 +3894,14 @@ static struct ioctl_trans *additional_ioctls;
 
 /* Always call these with kernel lock held! */
 
+
 int register_ioctl32_conversion(unsigned int cmd, int (*handler)(unsigned int, unsigned int, unsigned long, struct file *))
 {
 	int i;
 	if (!additional_ioctls) {
-		additional_ioctls = module_map(PAGE_SIZE);
+		additional_ioctls = (struct ioctl_trans *)get_zeroed_page(GFP_KERNEL);
 		if (!additional_ioctls)
 			return -ENOMEM;
-		memset(additional_ioctls, 0, PAGE_SIZE);
 	}
 	for (i = 0; i < PAGE_SIZE/sizeof(struct ioctl_trans); i++)
 		if (!additional_ioctls[i].cmd)
@@ -3767,13 +3910,15 @@ int register_ioctl32_conversion(unsigned int cmd, int (*handler)(unsigned int, u
 		return -ENOMEM;
 	additional_ioctls[i].cmd = cmd;
 	if (!handler)
-		additional_ioctls[i].handler = (u32)(long)sys_ioctl;
+		additional_ioctls[i].handler = 
+	    (int (*)(unsigned,unsigned,unsigned long, struct file *))sys_ioctl;
 	else
-		additional_ioctls[i].handler = (u32)(long)handler;
+		additional_ioctls[i].handler = handler;
 	ioctl32_insert_translation(&additional_ioctls[i]);
 	return 0;
 }
 
+
 int unregister_ioctl32_conversion(unsigned int cmd)
 {
 	unsigned long hash = ioctl32_hash(cmd);
@@ -3799,6 +3944,9 @@ int unregister_ioctl32_conversion(unsigned int cmd)
 	return -EINVAL;
 }
 
+EXPORT_SYMBOL(register_ioctl32_conversion); 
+EXPORT_SYMBOL(unregister_ioctl32_conversion); 
+
 asmlinkage int sys32_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
 {
 	struct file * filp;
@@ -3820,7 +3968,7 @@ asmlinkage int sys32_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
 	while (t && t->cmd != cmd)
 		t = (struct ioctl_trans *)(long)t->next;
 	if (t) {
-		handler = (void *)(long)t->handler;
+		handler = t->handler;
 		error = handler(fd, cmd, arg, filp);
 	} else {
 		static int count = 0;

arch/x86_64/ia32/ia32_signal.c

@@ -7,7 +7,7 @@
  *  2000-06-20  Pentium III FXSR, SSE support by Gareth Hughes
  *  2000-12-*   x86-64 compatibility mode signal handling by Andi Kleen
  * 
- *  $Id: ia32_signal.c,v 1.15 2001/10/16 23:41:42 ak Exp $
+ *  $Id: ia32_signal.c,v 1.17 2002/03/21 14:16:32 ak Exp $
  */
 
 #include <linux/sched.h>
@@ -29,6 +29,8 @@
 #include <asm/ptrace.h>
 #include <asm/ia32_unistd.h>
 #include <asm/user32.h>
+#include <asm/sigcontext32.h>
+#include <asm/fpu32.h>
 
 #define ptr_to_u32(x) ((u32)(u64)(x))	/* avoid gcc warning */ 
 
@@ -147,7 +149,7 @@ struct rt_sigframe
 };
 
 static int
-restore_sigcontext(struct pt_regs *regs, struct sigcontext_ia32 *sc, unsigned int *peax)
+ia32_restore_sigcontext(struct pt_regs *regs, struct sigcontext_ia32 *sc, unsigned int *peax)
 {
 	unsigned int err = 0;
 	
@@ -171,7 +173,13 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext_ia32 *sc, unsigned in
 	/* Reload fs and gs if they have changed in the signal handler.
 	   This does not handle long fs/gs base changes in the handler, but does not clobber 
 	   them at least in the normal case. */ 
-	RELOAD_SEG(gs);
+	
+	
+	{
+		unsigned short gs; 
+		err |= __get_user(gs, &sc->gs);
+		load_gs_index(gs); 
+	} 
 	RELOAD_SEG(fs);
 
 	COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
@@ -187,13 +195,13 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext_ia32 *sc, unsigned in
 
 	{
 		u32 tmp;
-		struct _fpstate * buf;
+		struct _fpstate_ia32 * buf;
 		err |= __get_user(tmp, &sc->fpstate);
-		buf = (struct _fpstate *) (u64)tmp;
+		buf = (struct _fpstate_ia32 *) (u64)tmp;
 		if (buf) {
 			if (verify_area(VERIFY_READ, buf, sizeof(*buf)))
 				goto badframe;
-			err |= restore_i387(buf);
+			err |= restore_i387_ia32(current, buf, 0);
 		}
 	}
 
@@ -228,7 +236,7 @@ asmlinkage int sys32_sigreturn(struct pt_regs regs)
 	recalc_sigpending();
 	spin_unlock_irq(&current->sigmask_lock);
 	
-	if (restore_sigcontext(&regs, &frame->sc, &eax))
+	if (ia32_restore_sigcontext(&regs, &frame->sc, &eax))
 		goto badframe;
 	return eax;
 
@@ -255,7 +263,7 @@ asmlinkage int sys32_rt_sigreturn(struct pt_regs regs)
 	recalc_sigpending();
 	spin_unlock_irq(&current->sigmask_lock);
 	
-	if (restore_sigcontext(&regs, &frame->uc.uc_mcontext, &eax))
+	if (ia32_restore_sigcontext(&regs, &frame->uc.uc_mcontext, &eax))
 		goto badframe;
 
 	if (__copy_from_user(&st, &frame->uc.uc_stack, sizeof(st)))
@@ -281,7 +289,7 @@ asmlinkage int sys32_rt_sigreturn(struct pt_regs regs)
  */
 
 static int
-setup_sigcontext(struct sigcontext_ia32 *sc, struct _fpstate_ia32 *fpstate,
+ia32_setup_sigcontext(struct sigcontext_ia32 *sc, struct _fpstate_ia32 *fpstate,
 		 struct pt_regs *regs, unsigned int mask)
 {
 	int tmp, err = 0;
@@ -306,7 +314,7 @@ setup_sigcontext(struct sigcontext_ia32 *sc, struct _fpstate_ia32 *fpstate,
 	err |= __put_user((u32)regs->eflags, &sc->eflags);
 	err |= __put_user((u32)regs->rsp, &sc->esp_at_signal);
 
-	tmp = save_i387(fpstate);
+	tmp = save_i387_ia32(current, fpstate, regs, 0);
 	if (tmp < 0)
 	  err = -EFAULT;
 	else
@@ -351,23 +359,24 @@ void ia32_setup_frame(int sig, struct k_sigaction *ka,
 {
 	struct sigframe *frame;
 	int err = 0;
-	struct exec_domain *exec_domain = current_thread_info()->exec_domain; 
 
 	frame = get_sigframe(ka, regs, sizeof(*frame));
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
 		goto give_sigsegv;
 
-	err |= __put_user((exec_domain
-		           && exec_domain->signal_invmap
-		           && sig < 32
-		           ? exec_domain->signal_invmap[sig]
+	{
+		struct exec_domain *ed = current_thread_info()->exec_domain;
+		
+		err |= __put_user((ed && ed->signal_invmap && sig < 32
+		           ? ed->signal_invmap[sig]
 		           : sig),
 		          &frame->sig);
+	}
 	if (err)
 		goto give_sigsegv;
 
-	err |= setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]);
+	err |= ia32_setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]);
 	if (err)
 		goto give_sigsegv;
 
@@ -419,19 +428,19 @@ void ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 {
 	struct rt_sigframe *frame;
 	int err = 0;
-	struct exec_domain *exec_domain = current_thread_info()->exec_domain; 
 
 	frame = get_sigframe(ka, regs, sizeof(*frame));
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
 		goto give_sigsegv;
 
-	err |= __put_user((exec_domain
-		    	   && exec_domain->signal_invmap
-		    	   && sig < 32
-		    	   ? exec_domain->signal_invmap[sig]
+	{
+		struct exec_domain *ed = current_thread_info()->exec_domain;
+		err |= __put_user((ed && ed->signal_invmap && sig < 32
+		    	   ? ed->signal_invmap[sig]
 			   : sig),
 			  &frame->sig);
+	}
 	err |= __put_user((u32)(u64)&frame->info, &frame->pinfo);
 	err |= __put_user((u32)(u64)&frame->uc, &frame->puc);
 	err |= ia32_copy_siginfo_to_user(&frame->info, info);
@@ -445,7 +454,7 @@ void ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	err |= __put_user(sas_ss_flags(regs->rsp),
 			  &frame->uc.uc_stack.ss_flags);
 	err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
-	err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
+	err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
 			        regs, set->sig[0]);
 	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
 	if (err)

arch/x86_64/ia32/ia32entry.S

 /*
  * Compatibility mode system call entry point for x86-64. 
  * 		
- * Copyright 2000,2001,2002 Andi Kleen, SuSE Labs.
+ * Copyright 2000,2001 Andi Kleen, SuSE Labs.
  * 
- * $Id: ia32entry.S,v 1.24 2001/11/11 17:47:47 ak Exp $ 		
+ * $Id: ia32entry.S,v 1.31 2002/03/24 13:01:45 ak Exp $ 		
  */		 
 
 #include <asm/calling.h>
 #include <asm/offset.h>
-#include <asm/thread_info.h>
+#include <asm/current.h>
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/ia32_unistd.h>	
+#include <asm/thread_info.h>	
 
 	.macro IA32_ARG_FIXUP
 	movl	%edi,%r8d
@@ -29,7 +30,7 @@
  */ 	
 ENTRY(ia32_cstar_target)
 	movq $-ENOSYS,%rax
-	SYSRET32
+	sysret
 	
 /* 
  * Emulated IA32 system calls via int 0x80. 
@@ -65,7 +66,6 @@ ia32_do_syscall:
 	cmpl $(IA32_NR_syscalls),%eax
 	jae  ia32_badsys
 	IA32_ARG_FIXUP
-	movl $1,%r10d
 	call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
 	movq %rax,RAX-ARGOFFSET(%rsp)
 	jmp int_ret_from_sys_call 
@@ -106,7 +106,7 @@ ni_syscall:
 	PTREGSCALL stub32_rt_sigsuspend, sys_rt_sigsuspend
 
 ENTRY(ia32_ptregs_common)
-	popq %r11	/* save return address outside the stack frame. */
+	popq %r11
 	SAVE_REST
 	movq %r11, %r15
 	call *%rax
@@ -241,14 +241,14 @@ ia32_sys_call_table:
 	.quad stub32_clone		/* 120 */
 	.quad sys_setdomainname
 	.quad sys_newuname
-	.quad ni_syscall	/* modify_ldt */
+	.quad sys_modify_ldt
 	.quad sys32_adjtimex
-	.quad sys_mprotect		/* 125 */
+	.quad sys32_mprotect		/* 125 */
 	.quad sys32_sigprocmask
-	.quad ni_syscall	/* query_module */
-	.quad ni_syscall	/* init_module */
-	.quad ni_syscall	/* delete module */
-	.quad ni_syscall	/* 130  get_kernel_syms */
+	.quad sys32_module_warning	/* create_module */
+	.quad sys32_module_warning	/* init_module */
+	.quad sys32_module_warning	/* delete module */
+	.quad sys32_module_warning	/* 130  get_kernel_syms */
 	.quad ni_syscall	/* quotactl */ 
 	.quad sys_getpgid
 	.quad sys_fchdir
@@ -287,7 +287,7 @@ ia32_sys_call_table:
 	.quad ni_syscall	/* vm86 */ 
 	.quad ni_syscall	/* query_module */
 	.quad sys_poll
-	.quad ni_syscall	/* nfsserverctl */ 
+	.quad sys32_nfsservctl
 	.quad sys_setresgid16	/* 170 */
 	.quad sys_getresgid16
 	.quad sys_prctl
@@ -302,8 +302,8 @@ ia32_sys_call_table:
 	.quad sys32_pwrite
 	.quad sys_chown16
 	.quad sys_getcwd
-	.quad ni_syscall	/* capget */
-	.quad ni_syscall	/* capset */
+	.quad sys_capget
+	.quad sys_capset
 	.quad stub32_sigaltstack
 	.quad sys32_sendfile
 	.quad ni_syscall		/* streams1 */
@@ -338,7 +338,7 @@ ia32_sys_call_table:
 	.quad sys_pivot_root
 	.quad sys_mincore
 	.quad sys_madvise
-	.quad sys_getdents64	/* 220 */ 
+	.quad sys_getdents64	/* 220 getdents64 */ 
 	.quad sys32_fcntl64	
 	.quad sys_ni_syscall	/* tux */
 	.quad sys_ni_syscall    /* security */
@@ -357,6 +357,10 @@ ia32_sys_call_table:
 	.quad sys_lremovexattr
 	.quad sys_fremovexattr
 	.quad sys_tkill		/* 238 */ 
+	.quad sys_sendfile64 
+	.quad sys_futex
+        .quad sys32_sched_setaffinity
+        .quad sys32_sched_getaffinity
 ia32_syscall_end:		
 	.rept IA32_NR_syscalls-(ia32_syscall_end-ia32_sys_call_table)/8
 		.quad ni_syscall

arch/x86_64/ia32/ptrace32.c

 /* 
  * 32bit ptrace for x86-64.
  *
- * Copyright 2001 Andi Kleen, SuSE Labs.
- * Some parts copied from arch/i386/kernel/ptrace.c. See that file for 
- * earlier copyright.
+ * Copyright 2001,2002 Andi Kleen, SuSE Labs.
+ * Some parts copied from arch/i386/kernel/ptrace.c. See that file for earlier 
+ * copyright.
  * 
- * This allows to access 64bit processes too but there is no way to see 
- * the extended register contents.
+ * This allows to access 64bit processes too; but there is no way to see the extended 
+ * register contents.
  *
- * $Id: ptrace32.c,v 1.2 2001/08/15 06:41:13 ak Exp $
+ * $Id: ptrace32.c,v 1.12 2002/03/24 13:02:02 ak Exp $
  */ 
 
 #include <linux/kernel.h>
 #include <linux/stddef.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
-#include <linux/mm.h>
-#include <linux/ptrace.h>
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 #include <asm/user32.h>
+#include <asm/user.h>
 #include <asm/errno.h>
 #include <asm/debugreg.h>
+#include <asm/i387.h>
+#include <asm/fpu32.h>
+#include <linux/mm.h>
 
 #define R32(l,q) \
 	case offsetof(struct user32, regs.l): stack[offsetof(struct pt_regs, q)/8] = val; break
@@ -139,7 +141,6 @@ static int getreg32(struct task_struct *child, unsigned regno, u32 *val)
 
 #undef R32
 
-
 static struct task_struct *find_target(int request, int pid, int *err)
 { 
 	struct task_struct *child;
@@ -154,23 +155,11 @@ static struct task_struct *find_target(int request, int pid, int *err)
 	if (child)
 		get_task_struct(child);
 	read_unlock(&tasklist_lock);
-	if (child) { 
-		*err = -ESRCH;
-		if (!(child->ptrace & PT_PTRACED))
-			goto out;
-		if (child->state != TASK_STOPPED) {
-			if (request != PTRACE_KILL)
-				goto out;
-		}
-		if (child->p_pptr != current)
-			goto out;
-
+	*err = ptrace_check_attach(child,0);
+	if (*err == 0)
 		return child; 
-	} 
- out:
 	put_task_struct(child);
 	return NULL; 
-	
 } 
 
 extern asmlinkage long sys_ptrace(long request, long pid, unsigned long addr, unsigned long data);
@@ -178,6 +167,7 @@ extern asmlinkage long sys_ptrace(long request, long pid, unsigned long addr, un
 asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 {
 	struct task_struct *child;
+	struct pt_regs *childregs; 
 	int ret;
 	__u32 val;
 
@@ -203,6 +193,8 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 	case PTRACE_SETREGS:
 	case PTRACE_SETFPREGS:
 	case PTRACE_GETFPREGS:
+	case PTRACE_SETFPXREGS:
+	case PTRACE_GETFPXREGS:
 		break;
 		
 	default:
@@ -213,11 +205,13 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 	if (!child)
 		return ret;
 
+	childregs = (struct pt_regs *)(child->thread.rsp0 - sizeof(struct pt_regs)); 
+
 	switch (request) {
 	case PTRACE_PEEKDATA:
 	case PTRACE_PEEKTEXT:
 		ret = 0;
-		if (access_process_vm(child, addr, &val, sizeof(u32), 0) != sizeof(u32))
+		if (access_process_vm(child, addr, &val, sizeof(u32), 0)!=sizeof(u32))
 			ret = -EIO;
 		else
 			ret = put_user(val, (unsigned int *)(u64)data); 
@@ -226,13 +220,13 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 	case PTRACE_POKEDATA:
 	case PTRACE_POKETEXT:
 		ret = 0;
-		if (access_process_vm(child, addr, &data, sizeof(u32), 1) != sizeof(u32))
+		if (access_process_vm(child, addr, &data, sizeof(u32), 1)!=sizeof(u32))
 			ret = -EIO; 
 		break;
 
 	case PTRACE_PEEKUSR:
 		ret = getreg32(child, addr, &val);
-		if (ret >= 0) 
+		if (ret == 0)
 			ret = put_user(val, (__u32 *)(unsigned long) data);
 		break;
 
@@ -242,7 +236,7 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 
 	case PTRACE_GETREGS: { /* Get all gp regs from the child. */
 		int i;
-	  	if (!access_ok(VERIFY_WRITE, (unsigned *)(unsigned long)data, FRAME_SIZE)) {
+	  	if (!access_ok(VERIFY_WRITE, (unsigned *)(unsigned long)data, 16*4)) {
 			ret = -EIO;
 			break;
 		}
@@ -258,10 +252,11 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 	case PTRACE_SETREGS: { /* Set all gp regs in the child. */
 		unsigned long tmp;
 		int i;
-	  	if (!access_ok(VERIFY_READ, (unsigned *)(unsigned long)data, FRAME_SIZE)) {
+	  	if (!access_ok(VERIFY_READ, (unsigned *)(unsigned long)data, 16*4)) {
 			ret = -EIO;
 			break;
 		}
+		empty_fpu(child); 
 		ret = 0; 
 		for ( i = 0; i <= 16*4; i += sizeof(u32) ) {
 			ret |= __get_user(tmp, (u32 *) (unsigned long) data);
@@ -271,35 +266,37 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 		break;
 	}
 
-#if 0 /* to be done. */
-	case PTRACE_GETFPREGS: { /* Get the child extended FPU state. */
-		if (!access_ok(VERIFY_WRITE, (unsigned *)data,
-			       sizeof(struct user_i387_struct))) {
-			ret = -EIO;
+	case PTRACE_SETFPREGS:
+		empty_fpu(child); 
+		save_i387_ia32(child, (void *)(u64)data, childregs, 1);
+		ret = 0; 
 			break;
-		}
-		if ( !child->used_math ) {
-			/* Simulate an empty FPU. */
-			set_fpu_cwd(child, 0x037f);
-			set_fpu_swd(child, 0x0000);
-			set_fpu_twd(child, 0xffff);
-			set_fpu_mxcsr(child, 0x1f80);
-		}
-		ret = get_fpregs((struct user_i387_struct *)data, child);
+
+	case PTRACE_GETFPREGS:
+		empty_fpu(child); 
+		restore_i387_ia32(child, (void *)(u64)data, 1);
+		ret = 0;
 		break;
-	}
 
-	case PTRACE_SETFPREGS: { /* Set the child extended FPU state. */
-		if (!access_ok(VERIFY_READ, (unsigned *)data,
-			       sizeof(struct user_i387_struct))) {
-			ret = -EIO;
+	case PTRACE_GETFPXREGS: { 
+		struct user32_fxsr_struct *u = (void *)(u64)data; 
+		empty_fpu(child); 
+		ret = copy_to_user(u, &child->thread.i387.fxsave, sizeof(*u));
+		ret |= __put_user(childregs->cs, &u->fcs);
+		ret |= __put_user(child->thread.ds, &u->fos); 
+		if (ret) 
+			ret = -EFAULT;
 		break; 
 	} 
-		child->used_math = 1;
-		ret = set_fpregs(child, (struct user_i387_struct *)data);
+	case PTRACE_SETFPXREGS: { 
+		struct user32_fxsr_struct *u = (void *)(u64)data; 
+		empty_fpu(child); 
+		/* no error checking to be bug to bug compatible with i386 */ 
+		copy_from_user(&child->thread.i387.fxsave, u, sizeof(*u));
+	        child->thread.i387.fxsave.mxcsr &= 0xffbf;
+		ret = 0; 
 			break;
-
-#endif
+		}
 
 	default:
 		ret = -EINVAL;

arch/x86_64/kernel/Makefile

@@ -19,8 +19,8 @@ export-objs     := mtrr.o msr.o cpuid.o x8664_ksyms.o
 
 obj-y	:= process.o semaphore.o signal.o entry.o traps.o irq.o \
 		ptrace.o i8259.o ioport.o ldt.o setup.o time.o sys_x86_64.o \
-		pci-dma.o x8664_ksyms.o i387.o syscall.o early_printk.o vsyscall.o \
-		setup64.o bluesmoke.o
+		pci-dma.o x8664_ksyms.o i387.o syscall.o vsyscall.o \
+		setup64.o bluesmoke.o bootflag.o
 
 ifdef CONFIG_PCI
 obj-y			+= pci-x86_64.o
@@ -33,6 +33,9 @@ obj-$(CONFIG_X86_CPUID)	+= cpuid.o
 obj-$(CONFIG_SMP)	+= smp.o smpboot.o trampoline.o
 obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o  nmi.o
 obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o mpparse.o
+#obj-$(CONFIG_ACPI)             += acpi.o
+#obj-$(CONFIG_ACPI_SLEEP)       += acpi_wakeup.o
+obj-$(CONFIG_EARLY_PRINTK)    += early_printk.o
 
 include $(TOPDIR)/Rules.make
 

arch/x86_64/kernel/apic.c

@@ -33,6 +33,8 @@
 /* Using APIC to generate smp_local_timer_interrupt? */
 int using_apic_timer = 0;
 
+int dont_enable_local_apic __initdata = 0;
+
 int prof_multiplier[NR_CPUS] = { 1, };
 int prof_old_multiplier[NR_CPUS] = { 1, };
 int prof_counter[NR_CPUS] = { 1, };
@@ -51,7 +53,7 @@ int get_maxlvt(void)
 void clear_local_APIC(void)
 {
 	int maxlvt;
-	unsigned long v;
+	unsigned int v;
 
 	maxlvt = get_maxlvt();
 
@@ -90,7 +92,7 @@ void clear_local_APIC(void)
 		apic_write_around(APIC_LVTPC, APIC_LVT_MASKED);
 	v = GET_APIC_VERSION(apic_read(APIC_LVR));
 	if (APIC_INTEGRATED(v)) {	/* !82489DX */
-		if (maxlvt > 3)
+		if (maxlvt > 3)		/* Due to Pentium errata 3AP and 11AP. */
 			apic_write(APIC_ESR, 0);
 		apic_read(APIC_ESR);
 	}
@@ -130,7 +132,7 @@ void disconnect_bsp_APIC(void)
 
 void disable_local_APIC(void)
 {
-	unsigned long value;
+	unsigned int value;
 
 	clear_local_APIC();
 
@@ -223,7 +225,7 @@ extern void __error_in_apic_c (void);
  */
 void __init init_bsp_APIC(void)
 {
-	unsigned long value, ver;
+	unsigned int value, ver;
 
 	/*
 	 * Don't do the setup now if we have a SMP BIOS as the
@@ -262,7 +264,7 @@ void __init init_bsp_APIC(void)
 
 void __init setup_local_APIC (void)
 {
-	unsigned long value, ver, maxlvt;
+	unsigned int value, ver, maxlvt;
 
 	/* Pound the ESR really hard over the head with a big hammer - mbligh */
 	if (esr_disable) {
@@ -395,7 +397,7 @@ void __init setup_local_APIC (void)
 		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP. */
 			apic_write(APIC_ESR, 0);
 		value = apic_read(APIC_ESR);
-		printk("ESR value before enabling vector: %08lx\n", value);
+		printk("ESR value before enabling vector: %08x\n", value);
 
 		value = ERROR_APIC_VECTOR;      // enables sending errors
 		apic_write_around(APIC_LVTERR, value);
@@ -405,7 +407,7 @@ void __init setup_local_APIC (void)
 		if (maxlvt > 3)
 			apic_write(APIC_ESR, 0);
 		value = apic_read(APIC_ESR);
-		printk("ESR value after enabling vector: %08lx\n", value);
+		printk("ESR value after enabling vector: %08x\n", value);
 	} else {
 		if (esr_disable)	
 			/* 
@@ -449,6 +451,7 @@ static struct {
 	unsigned int apic_lvterr;
 	unsigned int apic_tmict;
 	unsigned int apic_tdcr;
+	unsigned int apic_thmr;
 } apic_pm_state;
 
 static void apic_pm_suspend(void *data)
@@ -470,6 +473,7 @@ static void apic_pm_suspend(void *data)
 	apic_pm_state.apic_lvterr = apic_read(APIC_LVTERR);
 	apic_pm_state.apic_tmict = apic_read(APIC_TMICT);
 	apic_pm_state.apic_tdcr = apic_read(APIC_TDCR);
+	apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
 	__save_flags(flags);
 	__cli();
 	disable_local_APIC();
@@ -498,6 +502,7 @@ static void apic_pm_resume(void *data)
 	apic_write(APIC_SPIV, apic_pm_state.apic_spiv);
 	apic_write(APIC_LVT0, apic_pm_state.apic_lvt0);
 	apic_write(APIC_LVT1, apic_pm_state.apic_lvt1);
+	apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr);
 	apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc);
 	apic_write(APIC_LVTT, apic_pm_state.apic_lvtt);
 	apic_write(APIC_TDCR, apic_pm_state.apic_tdcr);
@@ -586,7 +591,6 @@ static inline void apic_pm_init2(void) { }
 static int __init detect_init_APIC (void)
 {
 	u32 h, l, features;
-	int needs_pm = 0;
 	extern void get_cpu_vendor(struct cpuinfo_x86*);
 
 	/* Workaround for us being called before identify_cpu(). */
@@ -619,7 +623,6 @@ static int __init detect_init_APIC (void)
 			l &= ~MSR_IA32_APICBASE_BASE;
 			l |= MSR_IA32_APICBASE_ENABLE | APIC_DEFAULT_PHYS_BASE;
 			wrmsr(MSR_IA32_APICBASE, l, h);
-			needs_pm = 1;
 		}
 	}
 	/*
@@ -631,17 +634,13 @@ static int __init detect_init_APIC (void)
 		printk("Could not enable APIC!\n");
 		return -1;
 	}
-	set_bit(X86_FEATURE_APIC, &boot_cpu_data.x86_capability);
+	set_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
 	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
 	boot_cpu_id = 0;
 	if (nmi_watchdog != NMI_NONE)
 		nmi_watchdog = NMI_LOCAL_APIC;
 
 	printk("Found and enabled local APIC!\n");
-
-	if (needs_pm)
-		apic_pm_init1();
-
 	return 0;
 
 no_apic:
@@ -782,7 +781,7 @@ void __setup_APIC_LVTT(unsigned int clocks)
 
 void setup_APIC_timer(void * data)
 {
-	unsigned long clocks = (unsigned long) data, slice, t0, t1;
+	unsigned int clocks = (unsigned long) data, slice, t0, t1;
 	unsigned long flags;
 	int delta;
 
@@ -799,7 +798,8 @@ void setup_APIC_timer(void * data)
 	 */
 
 	slice = clocks / (smp_num_cpus+1);
-	printk("cpu: %d, clocks: %lu, slice: %lu\n", smp_processor_id(), clocks, slice);
+	printk("cpu: %d, clocks: %d, slice: %d\n",
+		smp_processor_id(), clocks, slice);
 
 	/*
 	 * Wait for IRQ0's slice:
@@ -822,7 +822,8 @@ void setup_APIC_timer(void * data)
 
 	__setup_APIC_LVTT(clocks);
 
-	printk("CPU%d<T0:%lu,T1:%lu,D:%d,S:%lu,C:%lu>\n", smp_processor_id(), t0, t1, delta, slice, clocks);
+	printk("CPU%d<T0:%u,T1:%u,D:%d,S:%u,C:%u>\n",
+			smp_processor_id(), t0, t1, delta, slice, clocks);
 
 	__restore_flags(flags);
 }
@@ -842,9 +843,9 @@ void setup_APIC_timer(void * data)
 
 int __init calibrate_APIC_clock(void)
 {
-	unsigned long long t1 = 0, t2 = 0;
-	long tt1, tt2;
-	long result;
+	unsigned long t1 = 0, t2 = 0;
+	int tt1, tt2;
+	int result;
 	int i;
 	const int LOOPS = HZ/10;
 
@@ -892,19 +893,23 @@ int __init calibrate_APIC_clock(void)
 
 	result = (tt1-tt2)*APIC_DIVISOR/LOOPS;
 
+	
+	printk("t1 = %ld t2 = %ld tt1 = %d tt2 = %d\n", t1, t2, tt1, tt2);  
+
+
 	if (cpu_has_tsc)
-		printk("..... CPU clock speed is %ld.%04ld MHz.\n",
-			((long)(t2-t1)/LOOPS)/(1000000/HZ),
-			((long)(t2-t1)/LOOPS)%(1000000/HZ));
+		printk("..... CPU clock speed is %d.%04d MHz.\n",
+			((int)(t2-t1)/LOOPS)/(1000000/HZ),
+			((int)(t2-t1)/LOOPS)%(1000000/HZ));
 
-	printk("..... host bus clock speed is %ld.%04ld MHz.\n",
+	printk("..... host bus clock speed is %d.%04d MHz.\n",
 		result/(1000000/HZ),
 		result%(1000000/HZ));
 
 	return result;
 }
 
-static unsigned long calibration_result;
+static unsigned int calibration_result;
 
 void __init setup_APIC_clocks (void)
 {
@@ -917,12 +922,12 @@ void __init setup_APIC_clocks (void)
 	/*
 	 * Now set up the timer for real.
 	 */
-	setup_APIC_timer((void *)calibration_result);
+	setup_APIC_timer((void *)(u64)calibration_result);
 
 	__sti();
 
 	/* and update all other cpus */
-	smp_call_function(setup_APIC_timer, (void *)calibration_result, 1, 1);
+	smp_call_function(setup_APIC_timer, (void *)(u64)calibration_result, 1, 1);
 }
 
 void __init disable_APIC_timer(void)
@@ -985,7 +990,7 @@ int setup_profiling_timer(unsigned int multiplier)
  * value into /proc/profile.
  */
 
-inline void smp_local_timer_interrupt(struct pt_regs * regs)
+inline void smp_local_timer_interrupt(struct pt_regs *regs)
 {
 	int user = user_mode(regs);
 	int cpu = smp_processor_id();
@@ -1041,7 +1046,7 @@ inline void smp_local_timer_interrupt(struct pt_regs * regs)
  */
 unsigned int apic_timer_irqs [NR_CPUS];
 
-void smp_apic_timer_interrupt(struct pt_regs regs)
+void smp_apic_timer_interrupt(struct pt_regs *regs)
 {
 	int cpu = smp_processor_id();
 
@@ -1061,7 +1066,7 @@ void smp_apic_timer_interrupt(struct pt_regs regs)
 	 * interrupt lock, which is the WrongThing (tm) to do.
 	 */
 	irq_enter(cpu, 0);
-	smp_local_timer_interrupt(&regs);
+	smp_local_timer_interrupt(regs);
 	irq_exit(cpu, 0);
 
 	if (softirq_pending(cpu))
@@ -1073,7 +1078,9 @@ void smp_apic_timer_interrupt(struct pt_regs regs)
  */
 asmlinkage void smp_spurious_interrupt(void)
 {
-	unsigned long v;
+	unsigned int v;
+	static unsigned long last_warning; 
+	static unsigned long skipped; 
 
 	/*
 	 * Check if this really is a spurious interrupt and ACK it
@@ -1085,8 +1092,13 @@ asmlinkage void smp_spurious_interrupt(void)
 		ack_APIC_irq();
 
 	/* see sw-dev-man vol 3, chapter 7.4.13.5 */
-	printk(KERN_INFO "spurious APIC interrupt on CPU#%d, should never happen.\n",
-			smp_processor_id());
+	if (last_warning+30*HZ < jiffies) { 
+		printk(KERN_INFO "spurious APIC interrupt on CPU#%d, %ld skipped.\n",
+		       smp_processor_id(), skipped);
+		last_warning = jiffies; 
+	} else { 
+		skipped++; 
+	} 
 }
 
 /*
@@ -1095,7 +1107,7 @@ asmlinkage void smp_spurious_interrupt(void)
 
 asmlinkage void smp_error_interrupt(void)
 {
-	unsigned long v, v1;
+	unsigned int v, v1;
 
 	/* First tickle the hardware, only then report what went on. -- REW */
 	v = apic_read(APIC_ESR);
@@ -1114,7 +1126,7 @@ asmlinkage void smp_error_interrupt(void)
 	   6: Received illegal vector
 	   7: Illegal register address
 	*/
-	printk (KERN_ERR "APIC error on CPU%d: %02lx(%02lx)\n",
+	printk (KERN_ERR "APIC error on CPU%d: %02x(%02x)\n",
 	        smp_processor_id(), v , v1);
 }
 

arch/x86_64/kernel/bluesmoke.c

@@ -3,16 +3,127 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/config.h>
+#include <linux/irq.h>
 #include <asm/processor.h> 
+#include <asm/system.h>
 #include <asm/msr.h>
+#include <asm/apic.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
 
 static int mce_disabled __initdata = 0;
 
+static int banks;
+
 /*
- *	Machine Check Handler For PII/PIII/K7
+ * If we get an MCE, we don't know what state the caches/TLB's are
+ * going to be in, so we throw them all away.
  */
+static void inline flush_all (void)
+{   
+	__asm__ __volatile__ ("invd": : );
+	__flush_tlb();
+}
 
-static int banks;
+/*
+ *	P4/Xeon Thermal transition interrupt handler
+ */
+
+static void intel_thermal_interrupt(struct pt_regs *regs)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+	u32 l, h;
+	unsigned int cpu = smp_processor_id();
+
+	ack_APIC_irq();
+
+	rdmsr(MSR_IA32_THERM_STATUS, l, h);
+	if (l & 1) {
+		printk(KERN_EMERG "CPU#%d: Temperature above threshold\n", cpu);
+		printk(KERN_EMERG "CPU#%d: Running in modulated clock mode\n", cpu);
+	} else {
+		printk(KERN_INFO "CPU#%d: Temperature/speed normal\n", cpu);
+	}
+#endif
+}
+
+static void unexpected_thermal_interrupt(struct pt_regs *regs)
+{	
+	printk(KERN_ERR "CPU#%d: Unexpected LVT TMR interrupt!\n", smp_processor_id());
+}
+
+/*
+ *	Thermal interrupt handler for this CPU setup
+ */
+
+static void (*vendor_thermal_interrupt)(struct pt_regs *regs) = unexpected_thermal_interrupt;
+
+asmlinkage void smp_thermal_interrupt(struct pt_regs regs)
+{
+	vendor_thermal_interrupt(&regs);
+}
+
+/* P4/Xeon Thermal regulation detect and init */
+
+static void __init intel_init_thermal(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+	u32 l, h;
+	unsigned int cpu = smp_processor_id();
+
+	/* Thermal monitoring */
+	if (!test_bit(X86_FEATURE_ACPI, &c->x86_capability))
+		return;	/* -ENODEV */
+	
+	/* Clock modulation */
+	if (!test_bit(X86_FEATURE_ACC, &c->x86_capability))
+		return;	/* -ENODEV */
+
+	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
+	/* first check if its enabled already, in which case there might
+	 * be some SMM goo which handles it, so we can't even put a handler
+	 * since it might be delivered via SMI already -zwanem.
+	 */
+
+	if (l & (1<<3)) {
+		printk(KERN_DEBUG "CPU#%d: Thermal monitoring already enabled\n", cpu);
+	} else {
+		wrmsr(MSR_IA32_MISC_ENABLE, l | (1<<3), h);
+		printk(KERN_INFO "CPU#%d: Thermal monitoring enabled\n", cpu);
+	}
+
+	/* check wether a vector already exists */	
+	l = apic_read(APIC_LVTTHMR);
+	if (l & 0xff) {
+		printk(KERN_DEBUG "CPU#%d: Thermal LVT already handled\n", cpu);
+		return; /* -EBUSY */
+	}
+	
+	wrmsr(MSR_IA32_MISC_ENABLE, l | (1<<3), h);
+	printk(KERN_INFO "CPU#%d: Thermal monitoring enabled\n", cpu);
+	
+	/* The temperature transition interrupt handler setup */
+	l = THERMAL_APIC_VECTOR;		/* our delivery vector */
+	l |= (APIC_DM_FIXED | APIC_LVT_MASKED);	/* we'll mask till we're ready */
+	apic_write_around(APIC_LVTTHMR, l);
+
+	rdmsr(MSR_IA32_THERM_INTERRUPT, l, h);
+	wrmsr(MSR_IA32_THERM_INTERRUPT, l | 0x3 , h);
+
+	/* ok we're good to go... */
+	vendor_thermal_interrupt = intel_thermal_interrupt;
+	l = apic_read(APIC_LVTTHMR);
+	apic_write_around(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
+
+	return;
+#endif
+}
+
+/*
+ *	Machine Check Handler For PII/PIII
+ */
 
 static void intel_machine_check(struct pt_regs * regs, long error_code)
 {
@@ -21,6 +132,8 @@ static void intel_machine_check(struct pt_regs * regs, long error_code)
 	u32 mcgstl, mcgsth;
 	int i;
 	
+	flush_all();
+
 	rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
 	if(mcgstl&(1<<0))	/* Recoverable ? */
 		recover=0;
@@ -41,13 +154,12 @@ static void intel_machine_check(struct pt_regs * regs, long error_code)
 			if(high&(1<<27))
 			{
 				rdmsr(MSR_IA32_MC0_MISC+i*4, alow, ahigh);
-				printk("[%08x%08x]", alow, ahigh);
+				printk("[%08x%08x]", ahigh, alow);
 			}
 			if(high&(1<<26))
 			{
 				rdmsr(MSR_IA32_MC0_ADDR+i*4, alow, ahigh);
-				printk(" at %08x%08x", 
-					ahigh, alow);
+				printk(" at %08x%08x", ahigh, alow);
 			}
 			printk("\n");
 			/* Clear it */
@@ -66,9 +178,13 @@ static void intel_machine_check(struct pt_regs * regs, long error_code)
 	wrmsr(MSR_IA32_MCG_STATUS,mcgstl, mcgsth);
 }
 
-static void unexpected_machine_check(struct pt_regs *regs, long error_code)
+/*
+ *	Handle unconfigured int18 (should never happen)
+ */
+
+static void unexpected_machine_check(struct pt_regs * regs, long error_code)
 { 
-	printk("unexpected machine check %lx\n", error_code); 
+	printk(KERN_ERR "CPU#%d: Unexpected int18 (Machine Check).\n", smp_processor_id());
 } 
 
 /*
@@ -77,13 +193,60 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code)
  
 static void (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check;
 
-void do_machine_check(struct pt_regs * regs, long error_code)
+asmlinkage void do_machine_check(struct pt_regs * regs, long error_code)
 {
 	machine_check_vector(regs, error_code);
 }
 
+
+#ifdef CONFIG_X86_MCE_NONFATAL
+struct timer_list mce_timer;
+
+static void mce_checkregs (unsigned int cpu)
+{
+	u32 low, high;
+	int i;
+
+	if (cpu!=smp_processor_id())
+		BUG();
+
+	for (i=0; i<banks; i++) {
+		rdmsr(MSR_IA32_MC0_STATUS+i*4, low, high);
+
+		if ((low | high) != 0) {
+			flush_all();
+			printk (KERN_EMERG "MCE: The hardware reports a non fatal, correctable incident occured on CPU %d.\n", smp_processor_id());
+			printk (KERN_EMERG "Bank %d: %08x%08x\n", i, high, low);
+
+			/* Scrub the error so we don't pick it up in 5 seconds time. */
+			wrmsr(MSR_IA32_MC0_STATUS+i*4, 0UL, 0UL);
+
+			/* Serialize */
+			wmb();
+		}
+	}
+
+	/* Refresh the timer. */
+	mce_timer.expires = jiffies + 5 * HZ;
+	add_timer (&mce_timer);
+}
+
+static void mce_timerfunc (unsigned long data)
+{
+	int i;
+
+	for (i=0; i<smp_num_cpus; i++) {
+		if (i == smp_processor_id())
+			mce_checkregs(i);
+		else
+			smp_call_function (mce_checkregs, i, 1, 1);
+	}
+}
+#endif
+
+
 /*
- *	Set up machine check reporting for Intel processors
+ *	Set up machine check reporting for processors with Intel style MCE
  */
 
 static void __init intel_mcheck_init(struct cpuinfo_x86 *c)
@@ -96,14 +259,14 @@ static void __init intel_mcheck_init(struct cpuinfo_x86 *c)
 	 *	Check for MCE support
 	 */
 
-	if( !test_bit(X86_FEATURE_MCE, &c->x86_capability) )
+	if( !test_bit(X86_FEATURE_MCE, c->x86_capability) )
 		return;	
 	
 	/*
 	 *	Check for PPro style MCA
 	 */
 	 		
-	if( !test_bit(X86_FEATURE_MCA, &c->x86_capability) )
+	if( !test_bit(X86_FEATURE_MCA, c->x86_capability) )
 		return;
 		
 	/* Ok machine check is available */
@@ -114,19 +277,27 @@ static void __init intel_mcheck_init(struct cpuinfo_x86 *c)
 	if(done==0)
 		printk(KERN_INFO "Intel machine check architecture supported.\n");
 	rdmsr(MSR_IA32_MCG_CAP, l, h);
-	if(l&(1<<8))
+	if(l&(1<<8))	/* Control register present ? */
 		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
 	banks = l&0xff;
-	for(i=1;i<banks;i++)
-	{
+
+	/* Don't enable bank 0 on intel P6 cores, it goes bang quickly. */
+	if (c->x86_vendor == X86_VENDOR_INTEL && c->x86 == 6) {
+		for(i=1; i<banks; i++)
+			wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
+	} else {
+		for(i=0; i<banks; i++)
 		wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
 	}
-	for(i=0;i<banks;i++)
-	{
+
+	for(i=0; i<banks; i++)
 		wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
-	}
+
 	set_in_cr4(X86_CR4_MCE);
 	printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n", smp_processor_id());
+	
+	intel_init_thermal(c);
+
 	done=1;
 }
 
@@ -134,8 +305,6 @@ static void __init intel_mcheck_init(struct cpuinfo_x86 *c)
  *	This has to be run for each processor
  */
 
-
-
 void __init mcheck_init(struct cpuinfo_x86 *c)
 {
 	if(mce_disabled==1)
@@ -144,15 +313,23 @@ void __init mcheck_init(struct cpuinfo_x86 *c)
 	switch(c->x86_vendor)
 	{
 		case X86_VENDOR_AMD:
-			/*
-			 *	AMD K7 machine check is Intel like
-			 */
-			if(c->x86 == 6)
+			if(c->x86 == 6 || c->x86 == 15) {
 				intel_mcheck_init(c);
+#ifdef CONFIG_X86_MCE_NONFATAL
+				/* Set the timer to check for non-fatal errors every 5 seconds */
+				init_timer (&mce_timer);
+				mce_timer.expires = jiffies + 5 * HZ;
+				mce_timer.data = 0;
+				mce_timer.function = &mce_timerfunc;
+				add_timer (&mce_timer);
+#endif
+			}
 			break;
+
 		case X86_VENDOR_INTEL:
 			intel_mcheck_init(c);
 			break;
+
 		default:
 			break;
 	}

arch/x86_64/kernel/bootflag.c

+/*
+ *	Implement 'Simple Boot Flag Specification 1.0'
+ *
+ */
+
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <asm/io.h>
+
+#include <linux/mc146818rtc.h>
+
+
+#define SBF_RESERVED (0x78)
+#define SBF_PNPOS    (1<<0)
+#define SBF_BOOTING  (1<<1)
+#define SBF_DIAG     (1<<2)
+#define SBF_PARITY   (1<<7)
+
+
+struct sbf_boot
+{
+	u8 sbf_signature[4];
+	u32 sbf_len;
+	u8 sbf_revision __attribute((packed));
+	u8 sbf_csum __attribute((packed));
+	u8 sbf_oemid[6] __attribute((packed));
+	u8 sbf_oemtable[8] __attribute((packed));
+	u8 sbf_revdata[4] __attribute((packed));
+	u8 sbf_creator[4] __attribute((packed));
+	u8 sbf_crearev[4] __attribute((packed));
+	u8 sbf_cmos __attribute((packed));
+	u8 sbf_spare[3] __attribute((packed));
+};
+
+
+static int sbf_port __initdata = -1;
+
+static int __init sbf_struct_valid(unsigned long tptr)
+{
+	u8 *ap;
+	u8 v;
+	unsigned int i;
+	struct sbf_boot sb;
+	
+	memcpy_fromio(&sb, tptr, sizeof(sb));
+
+	if(sb.sbf_len != 40 && sb.sbf_len != 39)
+		// 39 on IBM ThinkPad A21m, BIOS version 1.02b (KXET24WW; 2000-12-19).
+		return 0;
+
+	ap = (u8 *)&sb;
+	v= 0;
+	
+	for(i=0;i<sb.sbf_len;i++)
+		v+=*ap++;
+		
+	if(v)
+		return 0;
+
+	if(memcmp(sb.sbf_signature, "BOOT", 4))
+		return 0;
+
+	if (sb.sbf_len == 39)
+		printk (KERN_WARNING "SBF: ACPI BOOT descriptor is wrong length (%d)\n",
+			sb.sbf_len);
+
+	sbf_port = sb.sbf_cmos;	/* Save CMOS port */
+	return 1;
+}
+
+static int __init parity(u8 v)
+{
+	int x = 0;
+	int i;
+	
+	for(i=0;i<8;i++)
+	{
+		x^=(v&1);
+		v>>=1;
+	}
+	return x;
+}
+
+static void __init sbf_write(u8 v)
+{
+	unsigned long flags;
+	if(sbf_port != -1)
+	{
+		v &= ~SBF_PARITY;
+		if(!parity(v))
+			v|=SBF_PARITY;
+
+		printk(KERN_INFO "SBF: Setting boot flags 0x%x\n",v);
+
+		spin_lock_irqsave(&rtc_lock, flags);
+		CMOS_WRITE(v, sbf_port);
+		spin_unlock_irqrestore(&rtc_lock, flags);
+	}
+}
+
+static u8 __init sbf_read(void)
+{
+	u8 v;
+	unsigned long flags;
+	if(sbf_port == -1)
+		return 0;
+	spin_lock_irqsave(&rtc_lock, flags);
+	v = CMOS_READ(sbf_port);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return v;
+}
+
+static int __init sbf_value_valid(u8 v)
+{
+	if(v&SBF_RESERVED)		/* Reserved bits */
+		return 0;
+	if(!parity(v))
+		return 0;
+	return 1;
+}
+
+
+static void __init sbf_bootup(void)
+{
+	u8 v;
+	if(sbf_port == -1)
+		return;
+	v = sbf_read();
+	if(!sbf_value_valid(v))
+		printk(KERN_WARNING "SBF: Simple boot flag value 0x%x read from CMOS RAM was invalid\n",v);
+	v &= ~SBF_RESERVED;
+	v &= ~SBF_BOOTING;
+	v &= ~SBF_DIAG;
+#if defined(CONFIG_ISAPNP)
+	v |= SBF_PNPOS;
+#endif
+	sbf_write(v);
+}
+
+static int __init sbf_init(void)
+{
+	unsigned int i;
+	void *rsdt;
+	u32 rsdtlen = 0;
+	u32 rsdtbase = 0;
+	u8 sum = 0;
+	int n;
+	
+	u8 *p;
+	
+	for(i=0xE0000; i <= 0xFFFE0; i+=16)
+	{
+		p = phys_to_virt(i);
+		
+		if(memcmp(p, "RSD PTR ", 8))
+			continue;
+		
+		sum = 0;
+		for(n=0; n<20; n++)
+			sum+=p[n];
+			
+		if(sum != 0)
+			continue;
+			
+		/* So it says RSD PTR and it checksums... */
+
+		/*
+		 *	Process the RDSP pointer
+		 */
+	 
+		rsdtbase = *(u32 *)(p+16);
+		
+		/*
+		 *	RSDT length is ACPI 2 only, for ACPI 1 we must map
+		 *	and remap.
+		 */
+		 
+		if(p[15]>1)
+			rsdtlen = *(u32 *)(p+20);
+		else
+			rsdtlen = 36;
+
+		if(rsdtlen < 36 || rsdtlen > 1024)
+			continue;
+		break;
+	}
+	if(i>0xFFFE0)
+		return 0;
+		
+		
+	rsdt = ioremap(rsdtbase, rsdtlen);
+	if(rsdt == 0)
+		return 0;
+		
+	i = readl(rsdt + 4);
+	
+	/*
+	 *	Remap if needed
+	 */
+	 
+	if(i > rsdtlen)
+	{
+		rsdtlen = i;
+		iounmap(rsdt);
+		rsdt = ioremap(rsdtbase, rsdtlen);
+		if(rsdt == 0)
+			return 0;
+	}
+	
+	for(n = 0; n < i; n++)
+		sum += readb(rsdt + n);
+		
+	if(sum)
+	{
+		iounmap(rsdt);
+		return 0;
+	}
+	
+	/* Ok the RSDT checksums too */
+	
+	for(n = 36; n+3 < i; n += 4)
+	{
+		unsigned long rp = readl(rsdt+n);
+		int len = 4096;
+
+		if(rp > 0xFFFFFFFFUL - len)
+			len = 0xFFFFFFFFUL - rp;
+			
+		/* Too close to the end!! */
+		if(len < 20)
+			continue;
+		rp = (unsigned long)ioremap(rp, 4096);
+		if(rp == 0)
+			continue;
+		if(sbf_struct_valid(rp))
+		{
+			/* Found the BOOT table and processed it */
+			printk(KERN_INFO "SBF: Simple Boot Flag extension found and enabled.\n");
+		}
+		iounmap((void *)rp);
+	}
+	iounmap(rsdt);
+	sbf_bootup();
+	return 0;
+}
+
+module_init(sbf_init);

arch/x86_64/kernel/cpuid.c

@@ -35,6 +35,7 @@
 #include <linux/poll.h>
 #include <linux/smp.h>
 #include <linux/major.h>
+#include <linux/fs.h>
 #include <linux/smp_lock.h>
 #include <linux/fs.h>
 

arch/x86_64/kernel/early_printk.c

+#define printk real_printk
 #include <asm/io.h>
+#undef printk
 
-/* This is "wrong" address to access it, we should access it using
-   0xffff8000000b8000ul; but 0xffff8000000b8000ul is not available
-   early at boot. */
-#define VGABASE		0xffffffff800b8000ul	
+
+#define VGABASE		0xffffffff800b8000ul	/* This is "wrong" address to access it, we should access it using 0xffff8000000b8000ul; but 0xffff8000000b8000ul is not available early at boot. */
 
 #define MAX_YPOS	25
 #define MAX_XPOS	80
@@ -62,6 +62,8 @@ early_puts (const char *str)
 
 static char buf[1024];
 
+int printk(const char *fmt, ...) __attribute__((alias("early_printk"))); 
+
 int early_printk(const char *fmt, ...)
 {
 	va_list args;

arch/x86_64/kernel/head.S

@@ -4,29 +4,30 @@
  *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
  *  Copyright (C) 2000 Pavel Machek <pavel@suse.cz>
  *  Copyright (C) 2000 Karsten Keil <kkeil@suse.de>
- *  Copyright (C) 2001 2002 Andi Kleen <ak@suse.de>
+ *  Copyright (C) 2001,2002 Andi Kleen <ak@suse.de>
  *
- *  $Id: head.S,v 1.41 2001/07/05 23:43:45 ak Exp $
+ *  $Id: head.S,v 1.49 2002/03/19 17:39:25 ak Exp $
  */
-.code64
-.text
+
 
 #include <linux/linkage.h>
 #include <linux/threads.h>
 #include <asm/desc.h>
 #include <asm/segment.h>
 #include <asm/page.h>
-#include <asm/offset.h>
+#include <asm/msr.h>
 	
-/* we don't able to switch in one step to final KERNEL ADDRESS SPACE
+/* we are not able to switch in one step to the final KERNEL ADRESS SPACE
  * because we need identity-mapped pages on setup so define __START_KERNEL to
  * 0x100000 for this stage
  * 
  */
 
-
+	.text
+	.code32
+/* %bx:	 1 if comming from smp trampoline on secondary cpu */ 
 startup_32:
-.code32
+	
 	/*
 	 * At this point the CPU runs in 32bit protected mode (CS.D = 1) with
 	 * paging disabled and the point of this file is to switch to 64bit
@@ -35,7 +36,9 @@ startup_32:
  	 * There is no stack until we set one up.
 	 */
 
-	/* As first check if extended functions are implemented */
+	movl %ebx,%ebp	/* Save trampoline flag */
+	
+	/* First check if extended functions are implemented */
 	movl	$0x80000000, %eax
 	cpuid
 	cmpl	$0x80000000, %eax
@@ -46,6 +49,8 @@ startup_32:
 	btl	$29, %edx
 	jnc	no_long_mode
 
+	movl	%edx,%edi
+	
 	/*
 	 * Prepare for entering 64bits mode
 	 */
@@ -61,14 +66,23 @@ startup_32:
 	movl	%eax, %cr3
 
 	/* Setup EFER (Extended Feature Enable Register) */
-	movl	$0xc0000080, %ecx
+	movl	$MSR_EFER, %ecx
 	rdmsr
 	/* Fool rdmsr and reset %eax to avoid dependences */
 	xorl	%eax, %eax
 	/* Enable Long Mode */
-	btsl	$8, %eax
+	btsl	$_EFER_LME, %eax
 	/* Enable System Call */
-	btsl	$0, %eax
+	btsl	$_EFER_SCE, %eax
+
+#if 0
+	/* No Execute supported? */	
+	btl	$20,%edi
+	jnc     1f
+	btsl	$_EFER_NX, %eax
+1:	
+#endif
+				
 	/* Make changes effective */
 	wrmsr
 
@@ -99,27 +113,37 @@ reach_compatibility_mode:
 	 * the new gdt/idt that has __KERNEL_CS with CS.L = 1.
 	 */
 
+	testw %bp,%bp	/* secondary CPU? */ 
+	jnz   second	
+	
 	/* Load new GDT with the 64bit segment using 32bit descriptor */
 	/* to avoid 32bit relocations we use fixed adresses here */
 	movl	$0x100F00, %eax
 	lgdt	(%eax)
+
 	movl    $0x100F10, %eax
 	/* Finally jump in 64bit mode */
 	ljmp	*(%eax)
 
-.code64
-reach_long64:
-	/*
-	 * Where we're running at 0x0000000000100000, and yes, finally
-	 * in 64bit mode.
-	 */
-	.globl	init_rsp
+second:
+	/* abuse syscall to get into 64bit mode. this way we don't need
+	   a working low identity mapping just for the short 32bit roundtrip. 
+	   XXX kludge. this should not be needed. */
+	movl  $MSR_STAR,%ecx
+	xorl  %eax,%eax
+	movl  $(__USER32_CS<<16)|__KERNEL_CS,%edx
+	wrmsr
 
-	/* Setup the first kernel stack (this instruction is modified by smpboot) */
-	.byte 0x48, 0xb8	/* movq *init_rsp,%rax */ 
-init_rsp:
-	.quad init_thread_union+THREAD_SIZE
-	movq	%rax, %rsp
+	movl  $MSR_CSTAR,%ecx
+	movl  $0xffffffff,%edx
+	movl  $0x80100100,%eax	# reach_long64 absolute
+	wrmsr
+	syscall
+
+	.code64
+	.org 0x100	
+reach_long64:
+	movq init_rsp(%rip),%rsp
 
 	/* zero EFLAGS after setting rsp */
 	pushq $0
@@ -133,15 +157,15 @@ init_rsp:
 	 */
 	lgdt	pGDT64
 
-	/* esi is pointer to real mode structure with interesting info.
-	   pass it to C */
-	movl	%esi, %edi
-
 	movl $__KERNEL_DS,%eax
-	movl %eax,%ss
 	movl %eax,%ds	
+	movl %eax,%ss
 	movl %eax,%es
 			
+	/* esi is pointer to real mode structure with interesting info.
+	   pass it to C */
+	movl	%esi, %edi
+	
 	/* Finally jump to run C code and to be on real kernel address
 	 * Since we are running on identity-mapped space we have to jump
 	 * to the full 64bit address , this is only possible as indirect
@@ -150,11 +174,14 @@ init_rsp:
 	movq	initial_code(%rip),%rax
 	jmp	*%rax
 
-
-	/* SMP bootup changes this */	
+	/* SMP bootup changes these two */	
 	.globl	initial_code
 initial_code:
 	.quad	x86_64_start_kernel
+	.globl init_rsp
+init_rsp:
+	.quad  init_thread_union+THREAD_SIZE-8
+
 
 .code32
 ENTRY(no_long_mode)
@@ -165,7 +192,7 @@ ENTRY(no_long_mode)
 .org 0xf00
 pGDT32:
 	.word	gdt32_end-gdt_table32
-	.quad	gdt_table32-__START_KERNEL+0x100000
+	.long	gdt_table32-__START_KERNEL+0x100000
 
 .org 0xf10	
 ljumpvector:
@@ -182,10 +209,9 @@ ENTRY(_stext)
 	 * 2Mbyte large pages provided by PAE mode)
 	 */
 .org 0x1000
-ENTRY(level4_pgt)
+ENTRY(init_level4_pgt)
 	.quad	0x0000000000102007		/* -> level3_ident_pgt */
 	.fill	255,8,0
-	/* __PAGE_OFFSET 0xffff800000000000 */
 	.quad	0x000000000010a007
 	.fill	254,8,0
 	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
@@ -193,7 +219,6 @@ ENTRY(level4_pgt)
 
 .org 0x2000
 /* Kernel does not "know" about 4-th level of page tables. */
-ENTRY(swapper_pg_dir)
 ENTRY(level3_ident_pgt)
 	.quad	0x0000000000104007
 	.fill	511,8,0
@@ -207,10 +232,8 @@ ENTRY(level3_kernel_pgt)
 
 .org 0x4000
 ENTRY(level2_ident_pgt)
-	/* 2 Mbytes are enough, this is necessary only for head.S */
+	/* 40MB for bootup. 	*/
 	.quad	0x0000000000000283
-	/* .fill	511,8,0 */
-	/* Jan needs more than 2Mbytes, so set a 40Mbyte mapping instead */
 	.quad	0x0000000000200183
 	.quad	0x0000000000400183
 	.quad	0x0000000000600183
@@ -230,10 +253,15 @@ ENTRY(level2_ident_pgt)
 	.quad	0x0000000002200183
 	.quad	0x0000000002400183
 	.quad	0x0000000002600183
+	/* Temporary mappings for the super early allocator in arch/x86_64/mm/init.c */
+	.globl temp_boot_pmds
+temp_boot_pmds:
 	.fill	492,8,0
 	
 .org 0x5000
 ENTRY(level2_kernel_pgt)
+	/* 40MB kernel mapping. The kernel code cannot be bigger than that.
+	   When you change this change KERNEL_TEXT_SIZE in pgtable.h too. */
 	/* (2^48-(2*1024*1024*1024)-((2^39)*511)-((2^30)*510)) = 0 */
 	.quad	0x0000000000000183
 	.quad	0x0000000000200183
@@ -255,11 +283,7 @@ ENTRY(level2_kernel_pgt)
 	.quad	0x0000000002200183
 	.quad	0x0000000002400183
 	.quad	0x0000000002600183
-	/*
-	 * We could go ahead without any downside (except typing programmer
-	 * wise :) but 40Mbyte are just enough for the kernel statically
-	 * linked part (and extending it is trivial).
-	 */
+	/* Module mapping starts here */
 	.fill	492,8,0
 
 .org 0x6000
@@ -278,11 +302,7 @@ ENTRY(empty_bad_pmd_table)
 ENTRY(level3_physmem_pgt)
 	.quad	0x0000000000105007		/* -> level2_kernel_pgt (so that __va works even before pagetable_init) */
 
-
-
 .org 0xb000
-
-
 .data
 
 .globl SYMBOL_NAME(gdt)
@@ -317,16 +337,17 @@ ENTRY(gdt_table)
 	.quad	0x00cffe000000ffff	/* __USER32_CS */
 	.quad	0x00cff2000000ffff	/* __USER_DS, __USER32_DS  */		
 	.quad	0x00affa000000ffff	/* __USER_CS */
+	.word	0xFFFF				# 4Gb - (0x100000*0x1000 = 4Gb)
+	.word	0				# base address = 0
+	.word	0x9A00				# code read/exec
+	.word	0x00CF				# granularity = 4096, 386
+						#  (+5th nibble of limit)
+					/* __KERNEL32_CS */
 
 	.globl  tss_start
 tss_start:
 	.rept NR_CPUS	 	
-	.quad   0,0					/* TSS descriptors. filled in later */
-	.endr
-	.globl ldt_start
-ldt_start:	
-	.rept NR_CPUS
-	.quad   0,0					/* LDT descriptors. filled in later */ 
+	.quad   0,0,0,0,0,0,0,0		/* TSS/LDT/per cpu entries. filled in later */
 	.endr	
 gdt_end:	
 	.globl gdt_end
@@ -337,6 +358,3 @@ ENTRY(idt_table)
 	.quad   0
 	.quad 	0
 	.endr
-	
-.section .text.lock
-ENTRY(stext_lock)

arch/x86_64/kernel/head64.c

@@ -64,7 +64,7 @@ static void __init setup_boot_cpu_data(void)
 	      (int *)&boot_cpu_data.x86_vendor_id[4]);
 
 	/* get cpu type */
-	cpuid(1, &eax, &dummy, &dummy, &boot_cpu_data.x86_capability[0]);
+	cpuid(1, &eax, &dummy, &dummy, (int *) &boot_cpu_data.x86_capability);
 	boot_cpu_data.x86 = (eax >> 8) & 0xf;
 	boot_cpu_data.x86_model = (eax >> 4) & 0xf;
 	boot_cpu_data.x86_mask = eax & 0xf;

arch/x86_64/kernel/init_task.c

@@ -7,7 +7,6 @@
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/desc.h>
-#include <asm/thread_info.h>
 
 static struct fs_struct init_fs = INIT_FS;
 static struct files_struct init_files = INIT_FILES;
@@ -15,7 +14,7 @@ static struct signal_struct init_signals = INIT_SIGNALS;
 struct mm_struct init_mm = INIT_MM(init_mm);
 
 /*
- * Initial thread structure.
+ * Initial task structure.
  *
  * We need to make sure that this is 8192-byte aligned due to the
  * way process stacks are handled. This is done by having a special
@@ -39,4 +38,9 @@ struct task_struct init_task = INIT_TASK(init_task);
  * section. Since TSS's are completely CPU-local, we want them
  * on exact cacheline boundaries, to eliminate cacheline ping-pong.
  */ 
-struct tss_struct init_tss[NR_CPUS] __cacheline_aligned = { [0 ... NR_CPUS-1] = INIT_TSS };
+struct tss_struct init_tss[NR_CPUS] __cacheline_aligned;
+
+
+#define ALIGN_TO_4K __attribute__((section(".data.init_task")))
+
+pgd_t boot_vmalloc_pgt[512]  ALIGN_TO_4K;

arch/x86_64/kernel/io_apic.c

@@ -67,7 +67,7 @@ static struct irq_pin_list {
  * shared ISA-space IRQs, so we have to support them. We are super
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
-static void add_pin_to_irq(unsigned int irq, int apic, int pin)
+static void __init add_pin_to_irq(unsigned int irq, int apic, int pin)
 {
 	static int first_free_entry = NR_IRQS;
 	struct irq_pin_list *entry = irq_2_pin + irq;

arch/x86_64/kernel/pci-dma.c

@@ -14,8 +14,6 @@ void *pci_alloc_consistent(struct pci_dev *hwdev, size_t size,
 	void *ret;
 	int gfp = GFP_ATOMIC;
 
-	/* We need to always allocate below 4Gig. We probably need new
-	   GPF mask to say that */ 
 	gfp |= GFP_DMA;
 	ret = (void *)__get_free_pages(gfp, get_order(size));
 

arch/x86_64/lib/Makefile

@@ -8,10 +8,9 @@
 L_TARGET = lib.a
 obj-y  = generic-checksum.o old-checksum.o delay.o \
 	usercopy.o getuser.o putuser.o  \
-	checksum_copy.o rwsem_thunk.o
+	checksum_copy.o thunk.o mmx.o
 
 obj-$(CONFIG_IO_DEBUG) += iodebug.o
-obj-$(CONFIG_X86_USE_3DNOW) += mmx.o
 obj-$(CONFIG_HAVE_DEC_LOCK) += dec_and_lock.o
 
 include $(TOPDIR)/Rules.make