[PATCH] x86_64 update

x86-64 updates for 2.5.58. Changes only x86-64 specific files.

 - Rewrote module allocation. Lots of bugs fixed. Module loading
   should work now again.
 - Kconfig help fixes from Randy Dunlap
 - Makefile cleanups from Pavel Machek and Sam Ravnborg
 - Assembly cleanups from Pavel
 - defconfig update
 - Better strlen_user/strnlen_user
 - Merge with i386: new ptrace commands, 32bit vsyscall signal trampolines
		new deactivate_mm, add asm/bug.h
 - Make sure initramfs is freed after booting (thanks to Kai for the hint)
 - User per cpu data for profile counters (Ravikiran Thirumalai)
 - 32bit compat_* updates from Stephen Rothwell
 - Fix race in context switch. The exception handler for bogus segment
   loads in __switch_to needs to keep interrupts disabled, otherwise an
   interrupt can deadlock on scheduler locks.  Also make sure they don't
   printk or set oops_in_progress during printk because printk does a
   wake_up too.
 - Disable 64bit GS base changes for processes.  I cannot get it to work
   reliably.
 - Clear IOPL on kernel entry

arch/x86_64/Kconfig

@@ -13,8 +13,8 @@ config X86_64
 	bool
 	default y
 	help
-	  Port to the x86-64 architecture. x86-64 is an 64bit extension to the
-	  classical 32bit x86 architecture. For details see http://www.x86-64.org
+	  Port to the x86-64 architecture. x86-64 is a 64-bit extension to the
+	  classical 32-bit x86 architecture. For details see http://www.x86-64.org
 
 config X86
 	bool
@@ -68,7 +68,7 @@ config EARLY_PRINTK
 	  for kernel debugging when your machine crashes very early before
 	  the console code is initialized. For normal operation it is not
 	  recommended because it looks ugly and doesn't cooperate with 
-	  klogd/syslogd or the X server.You should normally N here, unless
+	  klogd/syslogd or the X server. You should normally N here, unless
 	  you want to debug such a crash.
 	  
 
@@ -89,8 +89,8 @@ config MK8
 	bool "AMD-Hammer"
 	help
 	  Support for AMD Clawhammer/Sledgehammer CPUs. Only choice for x86-64
-	  currently so you should chose this if you want a x86-64 kernel. In fact
-	  you will have no other choice than to chose this.
+	  currently so you should choose this if you want a x86-64 kernel. In fact
+	  you will have no other choice than to choose this.
 
 config GENERIC_CPU
 	bool "Generic-x86-64"
@@ -165,7 +165,7 @@ config MTRR
 
 	  This code has a reasonably generic interface so that similar
 	  control registers on other processors can be easily supported
-	  as well:
+	  as well.
 
 	  Saying Y here also fixes a problem with buggy SMP BIOSes which only
 	  set the MTRRs for the boot CPU and not for the secondary CPUs. This
@@ -208,7 +208,7 @@ config SMP
 	  See also the <file:Documentation/smp.tex>,
 	  <file:Documentation/smp.txt>, <file:Documentation/i386/IO-APIC.txt>,
 	  <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at
-	  <http://www.linuxdoc.org/docs.html#howto>.
+	  <http://www.tldp.org/docs.html#howto>.
 
 	  If you don't know what to do here, say N.
 
@@ -252,7 +252,7 @@ config GART_IOMMU
 	bool "IOMMU support"
 	help
 	  Support the K8 IOMMU. Needed to run systems with more than 4GB of memory
-	  properly with 32bit devices. You should probably turn this on.
+	  properly with 32-bit devices. You should probably turn this on.
 	  The iommu can be turned off at runtime with the iommu=off parameter.
 
 config DUMMY_IOMMU
@@ -261,7 +261,7 @@ config DUMMY_IOMMU
 	default y
 	help
 	  Don't use IOMMU code. This will cause problems when you have more than 4GB 
-	  of memory and any 32bit devices. Don't turn on unless you know what you
+	  of memory and any 32-bit devices. Don't turn on unless you know what you
 	  are doing.
 
 config X86_MCE
@@ -287,7 +287,7 @@ config PM
 	  page on the WWW at
 	  <http://www.cs.utexas.edu/users/kharker/linux-laptop/> and the
 	  Battery Powered Linux mini-HOWTO, available from
-	  <http://www.linuxdoc.org/docs.html#howto>.
+	  <http://www.tldp.org/docs.html#howto>.
 
 	  Note that, even if you say N here, Linux on the x86 architecture
 	  will issue the hlt instruction if nothing is to be done, thereby
@@ -297,27 +297,27 @@ config SOFTWARE_SUSPEND
 	bool "Software Suspend (EXPERIMENTAL)"
 	depends on EXPERIMENTAL && PM
 	---help---
-	  Enable the possibilty of suspendig machine. It doesn't need APM.
+	  Enable the possibilty of suspending the machine. It doesn't need APM.
 	  You may suspend your machine by 'swsusp' or 'shutdown -z <time>' 
 	  (patch for sysvinit needed). 
 
-	  It creates an image which is saved in your active swaps. By the next
-	  booting the, pass 'resume=/path/to/your/swap/file' and kernel will 
-	  detect the saved image, restore the memory from
-	  it and then it continues to run as before you've suspended.
-	  If you don't want the previous state to continue use the 'noresume'
-	  kernel option. However note that your partitions will be fsck'd and
+	  It creates an image which is saved in your active swaps. On the next
+	  boot, pass the 'resume=/path/to/your/swap/file' option and the kernel
+	  will detect the saved image, restore the memory from
+	  it, and then continue to run as before you suspended.
+	  If you don't want the previous state to continue, use the 'noresume'
+	  kernel option. However, note that your partitions will be fsck'd and
 	  you must re-mkswap your swap partitions/files.
 
 	  Right now you may boot without resuming and then later resume but
-	  in meantime you cannot use those swap partitions/files which were
+	  in the meantime you cannot use those swap partitions/files which were
 	  involved in suspending. Also in this case there is a risk that buffers
 	  on disk won't match with saved ones.
 
-	  SMP is supported ``as-is''. There's a code for it but doesn't work.
-	  There have been problems reported relating SCSI.
+	  SMP is supported ``as-is''. There's code for it but doesn't work.
+	  There have been problems reported relating to SCSI.
 
-	  This option is about getting stable. However there is still some
+	  This option is close to getting stable. However there is still some
 	  absence of features.
 
 	  For more information take a look at Documentation/swsusp.txt.
@@ -338,7 +338,7 @@ config PCI
 	  VESA. If you have PCI, say Y, otherwise N.
 
 	  The PCI-HOWTO, available from
-	  <http://www.linuxdoc.org/docs.html#howto>, contains valuable
+	  <http://www.tldp.org/docs.html#howto>, contains valuable
 	  information about which PCI hardware does work under Linux and which
 	  doesn't.
 
@@ -357,8 +357,8 @@ config HOTPLUG
 	  the system is running, and be able to use them quickly.  In many
 	  cases, the devices can likewise be unplugged at any time too.
 
-	  One well known example of this is PCMCIA- or PC-cards, credit-card
-	  size devices such as network cards, modems or hard drives which are
+	  One well-known example of this is PCMCIA- or PC-cards, credit-card
+	  size devices such as network cards, modems, or hard drives which are
 	  plugged into slots found on all modern laptop computers.  Another
 	  example, used on modern desktops as well as laptops, is USB.
 
@@ -390,7 +390,7 @@ config KCORE_ELF
 
 	  You have two choices here: ELF and A.OUT. Selecting ELF will make
 	  /proc/kcore appear in ELF core format as defined by the Executable
-	  and Linking Format specification. Selecting A.OUT will choose the
+	  and Linkable Format specification. Selecting A.OUT will choose the
 	  old "a.out" format which may be necessary for some old versions
 	  of binutils or on some architectures.
 
@@ -416,7 +416,7 @@ config BINFMT_ELF
 	  want to say Y here.
 
 	  Information about ELF is contained in the ELF HOWTO available from
-	  <http://www.linuxdoc.org/docs.html#howto>.
+	  <http://www.tldp.org/docs.html#howto>.
 
 	  If you find that after upgrading from Linux kernel 1.2 and saying Y
 	  here, you still can't run any ELF binaries (they just crash), then
@@ -438,7 +438,7 @@ config BINFMT_MISC
 	  programs that need an interpreter to run like Java, Python or
 	  Emacs-Lisp. It's also useful if you often run DOS executables under
 	  the Linux DOS emulator DOSEMU (read the DOSEMU-HOWTO, available from
-	  <http://www.linuxdoc.org/docs.html#howto>). Once you have
+	  <http://www.tldp.org/docs.html#howto>). Once you have
 	  registered such a binary class with the kernel, you can start one of
 	  those programs simply by typing in its name at a shell prompt; Linux
 	  will automatically feed it to the correct interpreter.
@@ -458,8 +458,8 @@ config BINFMT_MISC
 config IA32_EMULATION
 	bool "IA32 Emulation"
 	help
-	  Include code to run 32bit programs under an 64bit kernel. You should likely
-	  turn this on, unless you're 100% sure that you don't have any 32bit programs
+	  Include code to run 32-bit programs under a 64-bit kernel. You should likely
+	  turn this on, unless you're 100% sure that you don't have any 32-bit programs
 	  left.
 
 config COMPAT
@@ -507,13 +507,13 @@ config IDE
 	  ATA Packet Interface (ATAPI) is a protocol used by EIDE tape and
 	  CD-ROM drives, similar in many respects to the SCSI protocol.
 
-	  SMART IDE (Self Monitoring, Analysis and Reporting Technology) was
+	  SMART IDE (Self-Monitoring, Analysis and Reporting Technology) was
 	  designed in order to prevent data corruption and disk crash by
-	  detecting pre hardware failure conditions (heat, access time, and
+	  detecting pre-hardware failure conditions (heat, access time, and
 	  the like...). Disks built since June 1995 may follow this standard.
-	  The kernel itself don't manage this; however there are quite a
+	  The kernel itself doesn't manage this; however there are quite a
 	  number of user programs such as smart that can query the status of
-	  SMART parameters disk.
+	  SMART parameters from disk drives.
 
 	  If you want to compile this driver as a module ( = code which can be
 	  inserted in and removed from the running kernel whenever you want),
@@ -563,7 +563,7 @@ source "drivers/message/fusion/Kconfig"
 
 source "drivers/ieee1394/Kconfig"
 
-#Currently not 64bit safe
+#Currently not 64-bit safe
 #source drivers/message/i2o/Config.in
 source "net/Kconfig"
 
@@ -600,11 +600,12 @@ config SOUND
 	  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
+	  <http://www.tldp.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.
+	  <file:Documentation/sound/oss/README.OSS> contains some slightly
+	  outdated but still useful information as well.  Newer sound
+	  driver documentation is found in <file:Documentation/sound/alsa/*>.
 
 	  If you have a PnP sound card and you want to configure it at boot
 	  time using the ISA PnP tools (read
@@ -613,7 +614,7 @@ config SOUND
 	  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
+	  as <file:Documentation/sound/oss/README.modules>; the module will be
 	  called soundcore.o.
 
 	  I'm told that even without a sound card, you can make your computer

arch/x86_64/Makefile

@@ -54,35 +54,31 @@ libs-y 					+= arch/x86_64/lib/
 core-y					+= arch/x86_64/kernel/ arch/x86_64/mm/
 core-$(CONFIG_IA32_EMULATION)		+= arch/x86_64/ia32/
 drivers-$(CONFIG_PCI)			+= arch/x86_64/pci/
-# FIXME: is drivers- right ?
 drivers-$(CONFIG_OPROFILE)		+= arch/x86_64/oprofile/
 
-makeboot =$(Q)$(MAKE) -f scripts/Makefile.build obj=arch/x86_64/boot $(1)
+boot := arch/x86_64/boot
 
-.PHONY: zImage bzImage compressed zlilo bzlilo zdisk bzdisk install \
-		clean archclean archmrproper
+.PHONY: bzImage bzlilo bzdisk install archmrproper
 
-BOOTIMAGE=arch/x86_64/boot/bzImage
-zImage zlilo zdisk: BOOTIMAGE=arch/x86_64/boot/zImage
+#Default target when executing "make"
+all: bzImage
 
-zImage bzImage: vmlinux
-	$(call makeboot,$(BOOTIMAGE))
+BOOTIMAGE                     := arch/x86_64/boot/bzImage
 
-compressed: zImage
+bzImage: vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) $(BOOTIMAGE)
 
-zlilo bzlilo: vmlinux
-	$(call makeboot,BOOTIMAGE=$(BOOTIMAGE) zlilo)
+bzlilo: vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) zlilo
 
-zdisk bzdisk: vmlinux
-	$(call makeboot,BOOTIMAGE=$(BOOTIMAGE) zdisk)
+bzdisk: vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) zdisk
 
 install: vmlinux
-	$(call makeboot,BOOTIMAGE=$(BOOTIMAGE) install)
+	$(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) $@
 
 archclean:
-	$(Q)$(MAKE) $(clean)=arch/i386/boot
-
-archmrproper:
+	$(Q)$(MAKE) $(clean)=$(boot)
 
 prepare: include/asm-$(ARCH)/offset.h
 
@@ -90,10 +86,10 @@ arch/$(ARCH)/kernel/asm-offsets.s: include/asm include/linux/version.h \
 				   include/config/MARKER
 
 include/asm-$(ARCH)/offset.h.tmp: arch/$(ARCH)/kernel/asm-offsets.s
-	@$(generate-asm-offsets.h) < $< > $@
 
-include/asm-$(ARCH)/offset.h: include/asm-$(ARCH)/offset.h.tmp
+include/asm-$(ARCH)/offset.h: arch/$(ARCH)/kernel/asm-offsets.s
 	@echo -n '  Generating $@'
+	@$(generate-asm-offsets.h) < $< > $@.tmp
 	@$(update-if-changed)
 
 CLEAN_FILES += include/asm-$(ARCH)/offset.h.tmp \

arch/x86_64/boot/Makefile

@@ -26,16 +26,14 @@ SVGA_MODE := -DSVGA_MODE=NORMAL_VGA
 #RAMDISK := -DRAMDISK=512
 
 EXTRA_TARGETS	:= vmlinux.bin bootsect bootsect.o \
-		   setup setup.o zImage bzImage
+		   setup setup.o bzImage
 
-CFLAGS += -m32
+EXTRA_CFLAGS := -m32
 
 host-progs	:= tools/build
-subdir-		:= compressed	#Let make clean descend in compressed/
+subdir-		:= compressed/	#Let make clean descend in compressed/
 # ---------------------------------------------------------------------------
 
-$(obj)/zImage:  IMAGE_OFFSET := 0x1000
-$(obj)/zImage:  EXTRA_AFLAGS := -traditional $(SVGA_MODE) $(RAMDISK)
 $(obj)/bzImage: IMAGE_OFFSET := 0x100000
 $(obj)/bzImage: EXTRA_AFLAGS := -traditional $(SVGA_MODE) $(RAMDISK) -D__BIG_KERNEL__
 $(obj)/bzImage: BUILDFLAGS   := -b
@@ -44,7 +42,7 @@ quiet_cmd_image = BUILD   $@
 cmd_image = $(obj)/tools/build $(BUILDFLAGS) $(obj)/bootsect $(obj)/setup \
 	    $(obj)/vmlinux.bin $(ROOT_DEV) > $@
 
-$(obj)/zImage $(obj)/bzImage: $(obj)/bootsect $(obj)/setup \
+$(obj)/bzImage: $(obj)/bootsect $(obj)/setup \
 			      $(obj)/vmlinux.bin $(obj)/tools/build FORCE
 	$(call if_changed,image)
 	@echo 'Kernel: $@ is ready'

arch/x86_64/boot/compressed/Makefile

@@ -11,7 +11,7 @@ EXTRA_AFLAGS	:= -traditional -m32
 
 # cannot use EXTRA_CFLAGS because base CFLAGS contains -mkernel which conflicts with
 # -m32
-CFLAGS := -m32 -D__KERNEL__ -I$(TOPDIR)/include -O2  
+CFLAGS := -m32 -D__KERNEL__ -Iinclude -O2  
 LDFLAGS := -m elf_i386
 
 LDFLAGS_vmlinux := -Ttext $(IMAGE_OFFSET) -e startup_32 -m elf_i386

arch/x86_64/defconfig

@@ -19,10 +19,16 @@ CONFIG_EXPERIMENTAL=y
 #
 # General setup
 #
-CONFIG_NET=y
 CONFIG_SYSVIPC=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 CONFIG_SYSCTL=y
+# CONFIG_LOG_BUF_SHIFT_17 is not set
+CONFIG_LOG_BUF_SHIFT_16=y
+# CONFIG_LOG_BUF_SHIFT_15 is not set
+# CONFIG_LOG_BUF_SHIFT_14 is not set
+# CONFIG_LOG_BUF_SHIFT_13 is not set
+# CONFIG_LOG_BUF_SHIFT_12 is not set
+CONFIG_LOG_BUF_SHIFT=16
 
 #
 # Loadable module support
@@ -85,6 +91,7 @@ CONFIG_ACPI_SYSTEM=y
 #
 CONFIG_PCI=y
 CONFIG_PCI_DIRECT=y
+# CONFIG_PCI_LEGACY_PROC is not set
 # CONFIG_PCI_NAMES is not set
 # CONFIG_HOTPLUG is not set
 
@@ -163,15 +170,14 @@ CONFIG_BLK_DEV_ADMA=y
 # CONFIG_BLK_DEV_AEC62XX is not set
 # CONFIG_BLK_DEV_ALI15X3 is not set
 CONFIG_BLK_DEV_AMD74XX=y
-# CONFIG_AMD74XX_OVERRIDE is not set
 # CONFIG_BLK_DEV_CMD64X is not set
+# CONFIG_BLK_DEV_TRIFLEX is not set
 # CONFIG_BLK_DEV_CY82C693 is not set
 # CONFIG_BLK_DEV_CS5520 is not set
 # CONFIG_BLK_DEV_HPT34X is not set
 # CONFIG_BLK_DEV_HPT366 is not set
 # CONFIG_BLK_DEV_SC1200 is not set
 # CONFIG_BLK_DEV_PIIX is not set
-# CONFIG_BLK_DEV_NFORCE is not set
 # CONFIG_BLK_DEV_NS87415 is not set
 # CONFIG_BLK_DEV_OPTI621 is not set
 # CONFIG_BLK_DEV_PDC202XX_OLD is not set
@@ -211,6 +217,11 @@ CONFIG_BLK_DEV_IDE_MODES=y
 #
 # CONFIG_IEEE1394 is not set
 
+#
+# Networking support
+#
+CONFIG_NET=y
+
 #
 # Networking options
 #
@@ -263,10 +274,6 @@ CONFIG_IPV6_SCTP__=y
 # Network testing
 #
 # CONFIG_NET_PKTGEN is not set
-
-#
-# Network device support
-#
 CONFIG_NETDEVICES=y
 
 #
@@ -286,8 +293,6 @@ CONFIG_NET_ETHERNET=y
 # CONFIG_HAPPYMEAL is not set
 # CONFIG_SUNGEM is not set
 # CONFIG_NET_VENDOR_3COM is not set
-# CONFIG_NET_VENDOR_SMC is not set
-# CONFIG_NET_VENDOR_RACAL is not set
 
 #
 # Tulip family network device support
@@ -296,6 +301,7 @@ CONFIG_NET_ETHERNET=y
 # CONFIG_HP100 is not set
 CONFIG_NET_PCI=y
 # CONFIG_PCNET32 is not set
+CONFIG_AMD8111_ETH=y
 # CONFIG_ADAPTEC_STARFIRE is not set
 # CONFIG_B44 is not set
 # CONFIG_DGRS is not set
@@ -315,7 +321,6 @@ CONFIG_8139TOO=m
 # CONFIG_SUNDANCE is not set
 # CONFIG_TLAN is not set
 # CONFIG_VIA_RHINE is not set
-# CONFIG_NET_POCKET is not set
 
 #
 # Ethernet (1000 Mbit)
@@ -343,7 +348,6 @@ CONFIG_TIGON3=y
 #
 # Token Ring devices (depends on LLC=y)
 #
-# CONFIG_NET_FC is not set
 # CONFIG_RCPCI is not set
 # CONFIG_SHAPER is not set
 
@@ -445,12 +449,25 @@ CONFIG_UNIX98_PTY_COUNT=256
 #
 # CONFIG_I2C is not set
 
+#
+# I2C Hardware Sensors Mainboard support
+#
+
+#
+# I2C Hardware Sensors Chip support
+#
+
 #
 # Mice
 #
 # CONFIG_BUSMOUSE is not set
 # CONFIG_QIC02_TAPE is not set
 
+#
+# IPMI
+#
+# CONFIG_IPMI_HANDLER is not set
+
 #
 # Watchdog Cards
 #
@@ -470,7 +487,6 @@ CONFIG_RTC=y
 # CONFIG_FTAPE is not set
 # CONFIG_AGP is not set
 # CONFIG_AGP_GART is not set
-# CONFIG_AGP3 is not set
 # CONFIG_DRM is not set
 # CONFIG_MWAVE is not set
 CONFIG_RAW_DRIVER=y
@@ -544,6 +560,7 @@ CONFIG_NFSD_V3=y
 # CONFIG_NFSD_V4 is not set
 CONFIG_NFSD_TCP=y
 CONFIG_SUNRPC=y
+# CONFIG_SUNRPC_GSS is not set
 CONFIG_LOCKD=y
 CONFIG_LOCKD_V4=y
 CONFIG_EXPORTFS=y

arch/x86_64/ia32/fpu32.c

@@ -80,9 +80,9 @@ static inline int convert_fxsr_from_user(struct i387_fxsave_struct *fxsave,
 	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);
+	err = __get_user(fxsave->cwd, &buf->cw); 
+	err |= __get_user(fxsave->swd, &buf->sw);
+	err |= __get_user(fxsave->twd, &buf->tag);
 	fxsave->twd = twd_i387_to_fxsr(fxsave->twd);
 	err |= __get_user(fxsave->rip, &buf->ipoff); 
 	err |= __get_user(fxsave->rdp, &buf->dataoff); 

arch/x86_64/ia32/ia32_signal.c

@@ -31,6 +31,7 @@
 #include <asm/user32.h>
 #include <asm/sigcontext32.h>
 #include <asm/fpu32.h>
+#include <asm/proto.h>
 
 #define ptr_to_u32(x) ((u32)(u64)(x))	/* avoid gcc warning */ 
 
@@ -405,18 +406,30 @@ void ia32_setup_frame(int sig, struct k_sigaction *ka,
 	if (err)
 		goto give_sigsegv;
 
-	/* Set up to return from userspace.  If provided, use a stub
-	   already in userspace.  */
-	if (ka->sa.sa_flags & SA_RESTORER) {
-		err |= __put_user((u32)(u64)ka->sa.sa_restorer, &frame->pretcode);
-	} else {
-		err |= __put_user((u32)(u64)frame->retcode, &frame->pretcode);
-		/* This is popl %eax ; movl $,%eax ; int $0x80 */
-		err |= __put_user((u16)0xb858, (short *)(frame->retcode+0));
-		err |= __put_user((u32)__NR_ia32_sigreturn, (int *)(frame->retcode+2));
-		err |= __put_user((u16)0x80cd, (short *)(frame->retcode+6));
+	/* Return stub is in 32bit vsyscall page */
+	{ 
+		void *restorer = syscall32_page + 32; 
+		if (ka->sa.sa_flags & SA_RESTORER)
+			restorer = ka->sa.sa_restorer;       
+		err |= __put_user(ptr_to_u32(restorer), &frame->pretcode);
+	}
+	/* These are actually not used anymore, but left because some 
+	   gdb versions depend on them as a marker. */
+	{ 
+		/* copy_to_user optimizes that into a single 8 byte store */
+		static const struct { 
+			u16 poplmovl;
+			u32 val;
+			u16 int80;    
+			u16 pad; 
+		} __attribute__((packed)) code = { 
+			0xb858,		 /* popl %eax ; movl $...,%eax */
+			__NR_ia32_sigreturn,   
+			0x80cd,		/* int $0x80 */
+			0,
+		}; 
+		err |= __copy_to_user(frame->retcode, &code, 8); 
 	}
-
 	if (err)
 		goto give_sigsegv;
 
@@ -486,18 +499,33 @@ void ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	if (err)
 		goto give_sigsegv;
 
-	/* Set up to return from userspace.  If provided, use a stub
-	   already in userspace.  */
-	if (ka->sa.sa_flags & SA_RESTORER) {
-		err |= __put_user((u32)(u64)ka->sa.sa_restorer, &frame->pretcode);
-	} else {
-		err |= __put_user(ptr_to_u32(frame->retcode), &frame->pretcode);
-		/* This is movl $,%eax ; int $0x80 */
-		err |= __put_user(0xb8, (char *)(frame->retcode+0));
-		err |= __put_user((u32)__NR_ia32_rt_sigreturn, (int *)(frame->retcode+1));
-		err |= __put_user(0x80cd, (short *)(frame->retcode+5));
+	
+	{ 
+		void *restorer = syscall32_page + 32; 
+		if (ka->sa.sa_flags & SA_RESTORER)
+			restorer = ka->sa.sa_restorer;       
+		err |= __put_user(ptr_to_u32(restorer), &frame->pretcode);
 	}
 
+	/* This is movl $,%eax ; int $0x80 */
+	/* Not actually used anymore, but left because some gdb versions
+	   need it. */ 
+	{ 
+		/* __copy_to_user optimizes that into a single 8 byte store */
+		static const struct { 
+			u8 movl; 
+			u32 val; 
+			u16 int80; 
+			u16 pad;
+			u8  pad2;				
+		} __attribute__((packed)) code = { 
+			0xb8,
+			__NR_ia32_rt_sigreturn,
+			0x80cd,
+			0,
+		}; 
+		err |= __copy_to_user(frame->retcode, &code, 8); 
+	} 
 	if (err)
 		goto give_sigsegv;
 

arch/x86_64/ia32/ia32entry.S

@@ -248,7 +248,7 @@ ia32_sys_call_table:
 	.quad sys_brk		/* 45 */
 	.quad sys_setgid16
 	.quad sys_getgid16
-	.quad ni_syscall	/* signal */
+	.quad sys_signal
 	.quad sys_geteuid16
 	.quad sys_getegid16	/* 50 */
 	.quad sys_acct
@@ -299,8 +299,8 @@ ia32_sys_call_table:
 	.quad sys_getpriority
 	.quad sys_setpriority
 	.quad ni_syscall			/* old profil syscall holder */
-	.quad sys32_statfs
-	.quad sys32_fstatfs		/* 100 */
+	.quad compat_sys_statfs
+	.quad compat_sys_fstatfs		/* 100 */
 	.quad sys_ioperm
 	.quad sys32_socketcall
 	.quad sys_syslog

arch/x86_64/ia32/sys_ia32.c

@@ -404,58 +404,6 @@ sys32_rt_sigprocmask(int how, sigset32_t *set, sigset32_t *oset,
 	return 0;
 }
 
-static int
-put_statfs (struct statfs32 *ubuf, struct statfs *kbuf)
-{
-	if (verify_area(VERIFY_WRITE, ubuf, sizeof(struct statfs32)) ||
-	    __put_user (kbuf->f_type, &ubuf->f_type) ||
-	    __put_user (kbuf->f_bsize, &ubuf->f_bsize) ||
-	    __put_user (kbuf->f_blocks, &ubuf->f_blocks) ||
-	    __put_user (kbuf->f_bfree, &ubuf->f_bfree) ||
-	    __put_user (kbuf->f_bavail, &ubuf->f_bavail) ||
-	    __put_user (kbuf->f_files, &ubuf->f_files) ||
-	    __put_user (kbuf->f_ffree, &ubuf->f_ffree) ||
-	    __put_user (kbuf->f_namelen, &ubuf->f_namelen) ||
-	    __put_user (kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
-	    __put_user (kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]))
-		return -EFAULT;
-	return 0;
-}
-
-extern asmlinkage long sys_statfs(const char * path, struct statfs * buf);
-
-asmlinkage long
-sys32_statfs(const char * path, struct statfs32 *buf)
-{
-	int ret;
-	struct statfs s;
-	mm_segment_t old_fs = get_fs();
-	
-	set_fs (KERNEL_DS);
-	ret = sys_statfs((const char *)path, &s);
-	set_fs (old_fs);
-	if (put_statfs(buf, &s))
-		return -EFAULT;
-	return ret;
-}
-
-extern asmlinkage long sys_fstatfs(unsigned int fd, struct statfs * buf);
-
-asmlinkage long
-sys32_fstatfs(unsigned int fd, struct statfs32 *buf)
-{
-	int ret;
-	struct statfs s;
-	mm_segment_t old_fs = get_fs();
-	
-	set_fs (KERNEL_DS);
-	ret = sys_fstatfs(fd, &s);
-	set_fs (old_fs);
-	if (put_statfs(buf, &s))
-		return -EFAULT;
-	return ret;
-}
-
 static inline long
 get_tv32(struct timeval *o, struct compat_timeval *i)
 {

arch/x86_64/ia32/syscall32.c

-/* Copyright 2002 Andi Kleen, SuSE Labs */
+/* Copyright 2002,2003 Andi Kleen, SuSE Labs */
 
 /* vsyscall handling for 32bit processes. Map a stub page into it 
    on demand because 32bit cannot reach the kernel's fixmaps */
@@ -8,8 +8,10 @@
 #include <linux/kernel.h>
 #include <linux/gfp.h>
 #include <linux/init.h>
+#include <linux/stringify.h>
 #include <asm/proto.h>
 #include <asm/tlbflush.h>
+#include <asm/ia32_unistd.h>
 
 /* 32bit SYSCALL stub mapped into user space. */ 
 asm("	.code32\n"
@@ -20,11 +22,26 @@ asm("	.code32\n"
     "	popl  %ebp\n"
     "	ret\n"
     "syscall32_end:\n"
+
+    /* signal trampolines */
+
+    "sig32_rt_tramp:\n"
+    "	movl $"  __stringify(__NR_ia32_rt_sigreturn) ",%eax\n"
+    "   int $0x80\n"
+    "sig32_rt_tramp_end:\n"
+
+    "sig32_tramp:\n"
+    "	popl %eax\n"
+    "	movl $"  __stringify(__NR_ia32_sigreturn) ",%eax\n"
+    "	int $0x80\n"
+    "sig32_tramp_end:\n"
     "	.code64\n"); 
 
 extern unsigned char syscall32[], syscall32_end[];
+extern unsigned char sig32_rt_tramp[], sig32_rt_tramp_end[];
+extern unsigned char sig32_tramp[], sig32_tramp_end[];
 
-static unsigned long syscall32_page; 
+char *syscall32_page; 
 
 /* RED-PEN: This knows too much about high level VM */ 
 /* Alternative would be to generate a vma with appropiate backing options
@@ -54,11 +71,16 @@ int map_syscall32(struct mm_struct *mm, unsigned long address)
 
 static int __init init_syscall32(void)
 { 
-	syscall32_page = get_zeroed_page(GFP_KERNEL); 
+	syscall32_page = (void *)get_zeroed_page(GFP_KERNEL); 
 	if (!syscall32_page) 
 		panic("Cannot allocate syscall32 page"); 
 	SetPageReserved(virt_to_page(syscall32_page));
-	memcpy((void *)syscall32_page, syscall32, syscall32_end - syscall32);
+	memcpy(syscall32_page, syscall32, syscall32_end - syscall32);
+	memcpy(syscall32_page + 32, sig32_rt_tramp, 
+	       sig32_rt_tramp_end - sig32_rt_tramp);
+	memcpy(syscall32_page + 64, sig32_tramp, 
+	       sig32_tramp_end - sig32_tramp);	
+	return 0;
 } 
 	
 __initcall(init_syscall32); 

arch/x86_64/kernel/Makefile

@@ -3,7 +3,7 @@
 #
 
 EXTRA_TARGETS 	:= head.o head64.o init_task.o
-
+EXTRA_AFLAGS  := -traditional
 export-objs     := x8664_ksyms.o pci-gart.o pci-dma.o
 
 obj-y	:= process.o semaphore.o signal.o entry.o traps.o irq.o \
@@ -32,4 +32,3 @@ $(obj)/bootflag.c:
 
 clean-files += bootflag.c
 
-EXTRA_AFLAGS := -traditional

arch/x86_64/kernel/apic.c

@@ -39,7 +39,7 @@ 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, };
+DEFINE_PER_CPU(int, prof_counter) =  1;
 
 int get_maxlvt(void)
 {
@@ -901,7 +901,7 @@ inline void smp_local_timer_interrupt(struct pt_regs *regs)
 
 	x86_do_profile(regs);
 
-	if (--prof_counter[cpu] <= 0) {
+	if (--per_cpu(prof_counter, cpu) <= 0) {
 		/*
 		 * The multiplier may have changed since the last time we got
 		 * to this point as a result of the user writing to
@@ -910,10 +910,11 @@ inline void smp_local_timer_interrupt(struct pt_regs *regs)
 		 *
 		 * Interrupts are already masked off at this point.
 		 */
-		prof_counter[cpu] = prof_multiplier[cpu];
-		if (prof_counter[cpu] != prof_old_multiplier[cpu]) {
-			__setup_APIC_LVTT(calibration_result/prof_counter[cpu]);
-			prof_old_multiplier[cpu] = prof_counter[cpu];
+		per_cpu(prof_counter, cpu) = prof_multiplier[cpu];
+		if (per_cpu(prof_counter, cpu) != prof_old_multiplier[cpu]) {
+			__setup_APIC_LVTT(calibration_result/
+					per_cpu(prof_counter, cpu));
+			prof_old_multiplier[cpu] = per_cpu(prof_counter, cpu);
 		}
 
 #ifdef CONFIG_SMP

arch/x86_64/kernel/entry.S

@@ -532,8 +532,10 @@ error_swapgs:
 	xorl %ebx,%ebx	
 	swapgs
 error_sti:	
+	bt $9,EFLAGS(%rsp)
+	jnc 1f
 	sti
-	movq %rdi,RDI(%rsp) 	
+1:	movq %rdi,RDI(%rsp) 	
 	movq %rsp,%rdi
 	movq ORIG_RAX(%rsp),%rsi	/* get error code */ 
 	movq $-1,ORIG_RAX(%rsp)

arch/x86_64/kernel/head.S

@@ -66,7 +66,7 @@ startup_32:
 	movl	%eax, %cr4
 
 	/* Setup early boot stage 4 level pagetables */
-	movl	$0x101000, %eax
+	movl	$(init_level4_pgt - __START_KERNEL_map), %eax
 	movl	%eax, %cr3
 
 	/* Setup EFER (Extended Feature Enable Register) */
@@ -89,20 +89,13 @@ startup_32:
 	wrmsr
 
 	xorl	%eax, %eax
-	/* Enable paging and in turn activate Long Mode */
-	btsl	$31, %eax
-	/* Enable protected mode */
-	btsl	$0, %eax
-	/* Enable MP */
-	btsl	$1, %eax
-	/* Enable ET */
-	btsl	$4, %eax
-	/* Enable NE */
-	btsl	$5, %eax
-	/* Enable WP */
-	btsl	$16, %eax
-	/* Enable AM */
-	btsl	$18, %eax
+	btsl	$31, %eax			/* Enable paging and in turn activate Long Mode */
+	btsl	$0, %eax			/* Enable protected mode */
+	btsl	$1, %eax			/* Enable MP */
+	btsl	$4, %eax			/* Enable ET */
+	btsl	$5, %eax			/* Enable NE */
+	btsl	$16, %eax			/* Enable WP */
+	btsl	$18, %eax			/* Enable AM */
 	/* Make changes effective */
 	movl	%eax, %cr0
 	jmp	reach_compatibility_mode
@@ -120,10 +113,10 @@ reach_compatibility_mode:
 	
 	/* Load new GDT with the 64bit segment using 32bit descriptor */
 	/* to avoid 32bit relocations we use fixed adresses here */
-	movl	$0x100F00, %eax
+	movl	$(pGDT32 - __START_KERNEL_map), %eax
 	lgdt	(%eax)
 
-	movl    $0x100F10, %eax
+	movl    $(ljumpvector - __START_KERNEL_map), %eax
 	/* Finally jump in 64bit mode */
 	ljmp	*(%eax)
 
@@ -205,11 +198,11 @@ ENTRY(no_long_mode)
 .org 0xf00
 pGDT32:
 	.word	gdt32_end-gdt_table32
-	.long	gdt_table32-__START_KERNEL+0x100000
+	.long	gdt_table32-__START_KERNEL_map
 
 .org 0xf10	
 ljumpvector:
-	.long	reach_long64-__START_KERNEL+0x100000
+	.long	reach_long64-__START_KERNEL_map
 	.word	__KERNEL_CS
 
 ENTRY(stext)

arch/x86_64/kernel/module.c

 /*  Kernel module help for x86-64
     Copyright (C) 2001 Rusty Russell.
-    Copyright (C) 2002 Andi Kleen, SuSE Labs.
+    Copyright (C) 2002,2003 Andi Kleen, SuSE Labs.
 
     This program is free software; you can redistribute it and/or modify
     it under the terms of the GNU General Public License as published by
@@ -22,9 +22,115 @@
 #include <linux/fs.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+#include <asm/system.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
 
 #define DEBUGP(fmt...) 
  
+void module_free(struct module *mod, void *module_region)
+{
+	struct vm_struct **prevp, *map;
+	int i;
+	unsigned long addr = (unsigned long)module_region;
+
+	if (!addr)
+		return;
+	write_lock(&vmlist_lock); 
+	for (prevp = &vmlist ; (map = *prevp) ; prevp = &map->next) {
+		if ((unsigned long)map->addr == addr) {
+			*prevp = map->next;
+			write_unlock(&vmlist_lock); 
+			goto found;
+		}
+	}
+	write_unlock(&vmlist_lock); 
+	printk("Trying to unmap nonexistent module vm area (%lx)\n", addr);
+	return;
+ found:
+	unmap_vm_area(map);
+	if (map->pages) {
+		for (i = 0; i < map->nr_pages; i++)
+			if (map->pages[i])
+				__free_page(map->pages[i]);	
+		kfree(map->pages);
+	}
+	kfree(map);					
+}
+
+void *module_alloc(unsigned long size)
+{
+	struct vm_struct **p, *tmp, *area;
+	struct page **pages;
+	void *addr;
+	unsigned int nr_pages, array_size, i;
+
+	if (!size)
+		return NULL; 
+	size = PAGE_ALIGN(size);
+	if (size > MODULES_LEN)
+		return NULL;
+
+	area = (struct vm_struct *) kmalloc(sizeof(*area), GFP_KERNEL);
+	if (!area)
+		return NULL;
+	memset(area, 0, sizeof(struct vm_struct));
+
+	write_lock(&vmlist_lock);
+	addr = (void *) MODULES_VADDR;
+	for (p = &vmlist; (tmp = *p); p = &tmp->next) {
+		void *next; 
+		DEBUGP("vmlist %p %lu addr %p\n", tmp->addr, tmp->size, addr);
+		if (size + (unsigned long) addr + PAGE_SIZE < (unsigned long) tmp->addr)
+			break;
+		next = (void *) (tmp->size + (unsigned long) tmp->addr);
+		if (next > addr) 
+			addr = next;
+	}
+
+	if ((unsigned long)addr + size >= MODULES_END) {
+		write_unlock(&vmlist_lock);
+		kfree(area); 
+		return NULL;
+	}
+	DEBUGP("addr %p\n", addr);
+
+	area->next = *p;
+	*p = area;
+	area->size = size + PAGE_SIZE;
+	area->addr = addr;
+	write_unlock(&vmlist_lock);
+
+	nr_pages = size >> PAGE_SHIFT;
+	array_size = (nr_pages * sizeof(struct page *));
+
+	area->nr_pages = nr_pages;
+	area->pages = pages = kmalloc(array_size, GFP_KERNEL);
+	if (!area->pages) 
+		goto fail;
+
+	memset(area->pages, 0, array_size);
+	for (i = 0; i < nr_pages; i++) {
+		area->pages[i] = alloc_page(GFP_KERNEL);
+		if (area->pages[i] == NULL)
+			goto fail;
+	}
+	
+	if (map_vm_area(area, PAGE_KERNEL_EXECUTABLE, &pages))
+		goto fail;
+	
+	memset(addr, 0, size);
+	DEBUGP("module_alloc size %lu = %p\n", size, addr);
+	return addr;
+
+fail:
+	module_free(NULL, addr);
+	return NULL;
+}
+
 /* We don't need anything special. */
 int module_frob_arch_sections(Elf_Ehdr *hdr,
 			      Elf_Shdr *sechdrs,

arch/x86_64/kernel/process.c

@@ -537,6 +537,11 @@ int sys_arch_prctl(int code, unsigned long addr)
 
 	switch (code) { 
 	case ARCH_SET_GS:
+#if 1
+		/* For now. We still have one unsolved bug in long gs base context
+		   switch handling. */
+		return -EINVAL; 
+#else
 		if (addr >= TASK_SIZE) 
 			return -EPERM; 
 		get_cpu();
@@ -546,6 +551,7 @@ int sys_arch_prctl(int code, unsigned long addr)
 		ret = checking_wrmsrl(MSR_KERNEL_GS_BASE, addr); 
 		put_cpu();
 		break;
+#endif
 	case ARCH_SET_FS:
 		/* Not strictly needed for fs, but do it for symmetry
 		   with gs */
@@ -594,15 +600,15 @@ static int get_free_idx(void)
  * Set a given TLS descriptor:
  * When you want addresses > 32bit use arch_prctl() 
  */
-asmlinkage int sys_set_thread_area(struct user_desc *u_info)
+int do_set_thread_area(struct thread_struct *t, struct user_desc *u_info)
 {
-	struct thread_struct *t = &current->thread;
 	struct user_desc info;
 	struct n_desc_struct *desc;
 	int cpu, idx;
 
 	if (copy_from_user(&info, u_info, sizeof(info)))
 		return -EFAULT;
+
 	idx = info.entry_number;
 
 	/*
@@ -634,12 +640,19 @@ asmlinkage int sys_set_thread_area(struct user_desc *u_info)
 		desc->a = LDT_entry_a(&info);
 		desc->b = LDT_entry_b(&info);
 	}
+	if (t == &current->thread)
 	load_TLS(t, cpu);
 
 	put_cpu();
 	return 0;
 }
 
+asmlinkage int sys_set_thread_area(struct user_desc *u_info)
+{ 
+	return do_set_thread_area(&current->thread, u_info); 
+} 
+
+
 /*
  * Get the current Thread-Local Storage area:
  */
@@ -661,7 +674,7 @@ asmlinkage int sys_set_thread_area(struct user_desc *u_info)
 #define GET_USEABLE(desc)	(((desc)->b >> 20) & 1)
 #define GET_LONGMODE(desc)	(((desc)->b >> 21) & 1)
 
-asmlinkage int sys_get_thread_area(struct user_desc *u_info)
+int do_get_thread_area(struct thread_struct *t, struct user_desc *u_info)
 {
 	struct user_desc info;
 	struct n_desc_struct *desc;
@@ -672,7 +685,7 @@ asmlinkage int sys_get_thread_area(struct user_desc *u_info)
 	if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
 		return -EINVAL;
 
-	desc = ((struct n_desc_struct *)current->thread.tls_array) + idx - GDT_ENTRY_TLS_MIN;
+	desc = ((struct n_desc_struct *)t->tls_array) + idx - GDT_ENTRY_TLS_MIN;
 
 	memset(&info, 0, sizeof(struct user_desc));
 	info.entry_number = idx;
@@ -691,6 +704,11 @@ asmlinkage int sys_get_thread_area(struct user_desc *u_info)
 	return 0;
 }
 
+asmlinkage int sys_get_thread_area(struct user_desc *u_info)
+{
+	return do_get_thread_area(&current->thread, u_info);
+} 
+
 /* 
  * Capture the user space registers if the task is not running (in user space)
  */

arch/x86_64/kernel/ptrace.c

@@ -23,6 +23,9 @@
 #include <asm/processor.h>
 #include <asm/i387.h>
 #include <asm/debugreg.h>
+#include <asm/ldt.h>
+#include <asm/desc.h>
+#include <asm/proto.h>
 
 /*
  * does not yet catch signals sent when the child dies.
@@ -319,6 +322,22 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
 		wake_up_process(child);
 		ret = 0;
 		break;
+	case PTRACE_SET_THREAD_AREA: {
+		int old; 
+		get_user(old,  &((struct user_desc *)data)->entry_number); 
+		put_user(addr, &((struct user_desc *)data)->entry_number);
+		ret = do_set_thread_area(&child->thread, 
+					 (struct user_desc *)data);
+		put_user(old,  &((struct user_desc *)data)->entry_number); 
+		break;
+	case PTRACE_GET_THREAD_AREA:
+		get_user(old,  &((struct user_desc *)data)->entry_number); 
+		put_user(addr, &((struct user_desc *)data)->entry_number);
+		ret = do_get_thread_area(&child->thread, 
+					 (struct user_desc *)data);
+		put_user(old,  &((struct user_desc *)data)->entry_number); 
+		break;
+	} 
 	}
 
 /*

arch/x86_64/kernel/setup64.c

@@ -200,7 +200,7 @@ void __init cpu_init (void)
 #endif
 
 	/* Flags to clear on syscall */
-	wrmsrl(MSR_SYSCALL_MASK, EF_TF|EF_DF|EF_IE); 
+	wrmsrl(MSR_SYSCALL_MASK, EF_TF|EF_DF|EF_IE|0x3000); 
 
 	wrmsrl(MSR_FS_BASE, 0);
 	wrmsrl(MSR_KERNEL_GS_BASE, 0);

arch/x86_64/kernel/smpboot.c

@@ -772,24 +772,16 @@ static void smp_tune_scheduling (void)
  * Cycle through the processors sending APIC IPIs to boot each.
  */
 
-extern int prof_multiplier[NR_CPUS];
-extern int prof_old_multiplier[NR_CPUS];
-extern int prof_counter[NR_CPUS];
-
 static void __init smp_boot_cpus(unsigned int max_cpus)
 {
 	int apicid, cpu;
 
 	/*
 	 * Initialize the logical to physical CPU number mapping
-	 * and the per-CPU profiling counter/multiplier
 	 */
 
 	for (apicid = 0; apicid < NR_CPUS; apicid++) {
 		x86_apicid_to_cpu[apicid] = -1;
-		prof_counter[apicid] = 1;
-		prof_old_multiplier[apicid] = 1;
-		prof_multiplier[apicid] = 1;
 	}
 
 	/*

arch/x86_64/kernel/traps.c

@@ -450,16 +450,20 @@ asmlinkage void do_int3(struct pt_regs * regs, long error_code)
 	do_trap(3, SIGTRAP, "int3", regs, error_code, NULL);
 }
 
+extern void dump_pagetable(unsigned long);
+
 asmlinkage void do_general_protection(struct pt_regs * regs, long error_code)
 {
 #ifdef CONFIG_CHECKING
        { 
                unsigned long gs; 
-               struct x8664_pda *pda = cpu_pda + stack_smp_processor_id(); 
+               struct x8664_pda *pda = cpu_pda + hard_smp_processor_id(); 
                rdmsrl(MSR_GS_BASE, gs); 
                if (gs != (unsigned long)pda) { 
                        wrmsrl(MSR_GS_BASE, pda); 
+		       oops_in_progress++;
                        printk("general protection handler: wrong gs %lx expected %p\n", gs, pda);
+		       oops_in_progress--;
                }
        }
 #endif

arch/x86_64/lib/Makefile

@@ -2,18 +2,15 @@
 # Makefile for x86_64-specific library files.
 #
 
-EXTRA_CFLAGS_csum-partial.o := -funroll-loops
+L_TARGET := lib.a
+export-objs := io.o csum-wrappers.o csum-partial.o
+
+CFLAGS_csum-partial.o := -funroll-loops
 
-L_TARGET = lib.a
-obj-y  = csum-partial.o csum-copy.o csum-wrappers.o delay.o \
+obj-y := csum-partial.o csum-copy.o csum-wrappers.o delay.o \
 	usercopy.o getuser.o putuser.o  \
 	thunk.o io.o clear_page.o copy_page.o bitstr.o
-obj-y += memcpy.o
-obj-y += memmove.o
-obj-y += memset.o
-obj-y += copy_user.o
-
-export-objs := io.o csum-wrappers.o csum-partial.o
+obj-y += memcpy.o memmove.o memset.o copy_user.o
 
 obj-$(CONFIG_IO_DEBUG) += iodebug.o
 obj-$(CONFIG_HAVE_DEC_LOCK) += dec_and_lock.o

arch/x86_64/lib/usercopy.c

@@ -109,19 +109,34 @@ unsigned long clear_user(void *to, unsigned long n)
 
 long strnlen_user(const char *s, long n)
 {
-	unsigned long res = 0;
+	long res = 0;
 	char c;
 
 	if (!access_ok(VERIFY_READ, s, n))
 		return 0;
 
 	while (1) {
+		if (res>n)
+			return n+1;
+		if (__get_user(c, s))
+			return 0;
+		if (!c)
+			return res+1;
+		res++;
+		s++;
+	}
+}
+
+long strlen_user(const char *s)
+{
+	long res = 0;
+	char c;
+
+	for (;;) {
 		if (get_user(c, s))
 			return 0;
 		if (!c)
 			return res+1;
-		if (res>n)
-			return n+1;
 		res++;
 		s++;
 	}

arch/x86_64/mm/Makefile

@@ -4,5 +4,5 @@
 
 export-objs := pageattr.o
 
-obj-y	 := init.o fault.o ioremap.o extable.o modutil.o pageattr.o
+obj-y	 := init.o fault.o ioremap.o extable.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o

arch/x86_64/mm/init.c

@@ -161,7 +161,6 @@ static  struct temp_map {
 } temp_mappings[] __initdata = { 
 	{ &temp_boot_pmds[0], (void *)(40UL * 1024 * 1024) },
 	{ &temp_boot_pmds[1], (void *)(42UL * 1024 * 1024) }, 
-	{ &temp_boot_pmds[2], (void *)(44UL * 1024 * 1024) }, 
 	{}
 }; 
 
@@ -316,8 +315,6 @@ void __init mem_init(void)
 	int codesize, reservedpages, datasize, initsize;
 	int tmp;
 
-	printk("mem_init\n");
-
 	if (!mem_map)
 		BUG();
 

arch/x86_64/mm/modutil.c

-/*  arch/x86_64/mm/modutil.c
- *
- *  Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
- *  Based upon code written by Linus Torvalds and others.
- * 
- *  Blatantly copied from sparc64 for x86-64 by Andi Kleen. 
- *  Should use direct mapping with 2MB pages. This would need extension
- *  of the kernel mapping.
- */
- 
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
-#include <linux/module.h>
-#include <linux/err.h>
-
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-
-/* FIXME: If module_region == mod->init_region, trim exception
-   table entries. */
-void module_free(struct module *mod, void *module_region)
-{
-	struct vm_struct **p, *tmp;
-	int i;
-	unsigned long addr = (unsigned long)module_region;
-
-	if (!addr)
-		return;
-	if ((PAGE_SIZE-1) & addr) {
-		printk("Trying to unmap module with bad address (%lx)\n", addr);
-		return;
-	}
-	write_lock(&vmlist_lock); 
-	for (p = &vmlist ; (tmp = *p) ; p = &tmp->next) {
-		if ((unsigned long)tmp->addr == addr) {
-			*p = tmp->next;
-			write_unlock(&vmlist_lock); 
-			goto found;
-		}
-	}
-	write_unlock(&vmlist_lock); 
-	printk("Trying to unmap nonexistent module vm area (%lx)\n", addr);
-	return;
- found:
-	unmap_vm_area(tmp);
-	for (i = 0; i < tmp->nr_pages; i++) {
-		if (unlikely(!tmp->pages[i]))
-			BUG();
-		__free_page(tmp->pages[i]);
-	}
-	
-	kfree(tmp->pages);
-	kfree(tmp);					
-}
-
-void * module_alloc (unsigned long size)
-{
-	struct vm_struct **p, *tmp, *area;
-	struct page **pages;
-	void * addr;
-	unsigned int nr_pages, array_size, i;
-
-	if (!size)
-		return NULL;
-	size = PAGE_ALIGN(size);
-	if (size > MODULES_LEN)
-		return ERR_PTR(-ENOMEM);
-		
-	addr = (void *) MODULES_VADDR;
-	for (p = &vmlist; (tmp = *p) ; p = &tmp->next) {
-		if (size + (unsigned long) addr < (unsigned long) tmp->addr)
-			break;
-		addr = (void *) (tmp->size + (unsigned long) tmp->addr);
-	}
-	if ((unsigned long) addr + size >= MODULES_END)
-		return ERR_PTR(-ENOMEM);
-	
-	area = (struct vm_struct *) kmalloc(sizeof(*area), GFP_KERNEL);
-	if (!area)
-		return ERR_PTR(-ENOMEM);
-	area->size = size + PAGE_SIZE;
-	area->addr = addr;
-	area->next = *p;
-	area->pages = NULL;
-	area->nr_pages = 0;
-	area->phys_addr = 0;
-	*p = area;
-
-	nr_pages = size >> PAGE_SHIFT;
-	array_size = (nr_pages * sizeof(struct page *));
-
-	area->nr_pages = nr_pages;
-	area->pages = pages = kmalloc(array_size, GFP_KERNEL);
-	if (!area->pages)
-		goto fail;
-
-	memset(area->pages, 0, array_size);
-
-	for (i = 0; i < area->nr_pages; i++) {
-		area->pages[i] = alloc_page(GFP_KERNEL);
-		if (unlikely(!area->pages[i]))
-			goto fail;
-	}
-	
-	if (map_vm_area(area, PAGE_KERNEL_EXECUTABLE, &pages)) {
-		unmap_vm_area(area);
-		goto fail;
-	}
-
-	memset(area->addr, 0, size);
-	return area->addr;
-
-fail:
-	if (area->pages) {
-		for (i = 0; i < area->nr_pages; i++) {
-			if (area->pages[i])
-				__free_page(area->pages[i]);
-		}
-		kfree(area->pages);
-	}
-	kfree(area);
-
-	return ERR_PTR(-ENOMEM);
-}
-

arch/x86_64/pci/Makefile

-
+#
+# Makefile for X86_64 specific PCI routines
+#
 obj-y		:= x86-64.o
-
-obj-$(CONFIG_PCI_DIRECT)	+= direct.o
-
+obj-$(CONFIG_PCI_DIRECT)+= direct.o
 obj-y		+= fixup.o
-
-ifdef	CONFIG_ACPI_PCI
-obj-y		+= acpi.o
-endif
-obj-y		+= legacy.o
-
-
-obj-y		+= irq.o common.o
+obj-$(CONFIG_ACPI_PCI)	+= acpi.o
+obj-y			+= legacy.o irq.o common.o

arch/x86_64/vmlinux.lds.S

@@ -73,11 +73,6 @@ SECTIONS
   . = ALIGN(4096); 
   .data.boot_pgt : { *(.data.boot_pgt) }
 
-  . = ALIGN(4096);
-  __initramfs_start = .;
-  .init.ramfs : { *(.init.ramfs) }
-  __initramfs_end = .;
-	
   . = ALIGN(4096);		/* Init code and data */
   __init_begin = .;
   .init.text : { *(.init.text) }
@@ -100,6 +95,10 @@ SECTIONS
 	*(.initcall7.init)
   }
   __initcall_end = .;
+  . = ALIGN(4096);
+  __initramfs_start = .;
+  .init.ramfs : { *(.init.ramfs) }
+  __initramfs_end = .;	
   . = ALIGN(32);
   __per_cpu_start = .;
   .data.percpu  : { *(.data.percpu) }

include/asm-x86_64/bug.h

+#ifndef __ASM_X8664_BUG_H
+#define __ASM_X8664_BUG_H 1
+
+#include <linux/stringify.h>
+
+/*
+ * Tell the user there is some problem.  The exception handler decodes 
+ * this frame.
+ */ 
+struct bug_frame { 
+       unsigned char ud2[2];          
+	/* should use 32bit offset instead, but the assembler doesn't 
+	   like it */ 
+	char *filename;   
+	unsigned short line; 
+} __attribute__((packed)); 
+
+#define BUG() \
+	asm volatile("ud2 ; .quad %c1 ; .short %c0" :: \
+		     "i"(__LINE__), "i" (__stringify(KBUILD_BASENAME)))
+#define PAGE_BUG(page) BUG()
+void out_of_line_bug(void);
+
+#endif

include/asm-x86_64/compat.h

@@ -68,4 +68,17 @@ struct compat_flock {
 	compat_pid_t	l_pid;
 };
 
+struct compat_statfs {
+	int		f_type;
+	int		f_bsize;
+	int		f_blocks;
+	int		f_bfree;
+	int		f_bavail;
+	int		f_files;
+	int		f_ffree;
+	compat_fsid_t	f_fsid;
+	int		f_namelen;	/* SunOS ignores this field. */
+	int		f_spare[6];
+};
+
 #endif /* _ASM_X86_64_COMPAT_H */

include/asm-x86_64/ia32.h

@@ -101,19 +101,6 @@ struct stat64 {
 } __attribute__((packed));
 
 
-struct statfs32 {
-       int f_type;
-       int f_bsize;
-       int f_blocks;
-       int f_bfree;
-       int f_bavail;
-       int f_files;
-       int f_ffree;
-       compat_fsid_t f_fsid;
-       int f_namelen;  /* SunOS ignores this field. */
-       int f_spare[6];
-};
-
 typedef union sigval32 {
 	int sival_int;
 	unsigned int sival_ptr;

include/asm-x86_64/mmu_context.h

@@ -62,7 +62,10 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 #endif
 }
 
-#define deactivate_mm(tsk,mm)	do { } while (0)
+#define deactivate_mm(tsk,mm)	do { \
+	load_gs_index(0); \
+	asm volatile("movl %0,%%fs"::"r"(0));  \
+} while(0)
 
 #define activate_mm(prev, next) \
 	switch_mm((prev),(next),NULL,smp_processor_id())

include/asm-x86_64/page.h

@@ -69,21 +69,7 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 
 #ifndef __ASSEMBLY__
 
-#include <linux/stringify.h>
-
-/*
- * Tell the user there is some problem.  The exception handler decodes this frame.
- */ 
-struct bug_frame { 
-       unsigned char ud2[2];          
-	char *filename;    /* should use 32bit offset instead, but the assembler doesn't like it */ 
-	unsigned short line; 
-} __attribute__((packed)); 
-#define BUG() \
-	asm volatile("ud2 ; .quad %c1 ; .short %c0" :: \
-		     "i"(__LINE__), "i" (__stringify(KBUILD_BASENAME)))
-#define PAGE_BUG(page) BUG()
-void out_of_line_bug(void);
+#include <asm/bug.h>
 
 /* Pure 2^n version of get_order */
 extern __inline__ int get_order(unsigned long size)

include/asm-x86_64/proto.h

@@ -43,6 +43,12 @@ extern void exception_table_check(void);
 extern int acpi_boot_init(char *);
 
 extern int map_syscall32(struct mm_struct *mm, unsigned long address);
+extern char *syscall32_page;
+
+struct thread_struct;
+
+int do_set_thread_area(struct thread_struct *t, struct user_desc *u_info);
+int do_get_thread_area(struct thread_struct *t, struct user_desc *u_info);
 
 #define round_up(x,y) (((x) + (y) - 1) & ~((y)-1))
 #define round_down(x,y) ((x) & ~((y)-1))

include/asm-x86_64/ptrace.h

@@ -78,6 +78,10 @@ struct pt_regs {
 #define PTRACE_GETFPXREGS         18
 #define PTRACE_SETFPXREGS         19
 
+#define PTRACE_GET_THREAD_AREA    25
+#define PTRACE_SET_THREAD_AREA    26
+
+
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__) 
 #define user_mode(regs) (!!((regs)->cs & 3))
 #define instruction_pointer(regs) ((regs)->rip)

include/asm-x86_64/segment.h

@@ -10,7 +10,7 @@
 
 /* 
  * we cannot use the same code segment descriptor for user and kernel
- * even not in the long flat model, because of different DPL /kkeil 
+ * -- not even in the long flat mode, because of different DPL /kkeil 
  * The segment offset needs to contain a RPL. Grr. -AK
  * GDT layout to get 64bit syscall right (sysret hardcodes gdt offsets) 
  */

include/asm-x86_64/uaccess.h

@@ -299,8 +299,8 @@ static inline int __copy_to_user(void *dst, const void *src, unsigned size)
 
 long strncpy_from_user(char *dst, const char *src, long count);
 long __strncpy_from_user(char *dst, const char *src, long count);
-#define strlen_user(str) strnlen_user(str, ~0UL >> 1)
 long strnlen_user(const char *str, long n);
+long strlen_user(const char *str);
 unsigned long clear_user(void *mem, unsigned long len);
 unsigned long __clear_user(void *mem, unsigned long len);