Merge branches 'x86/xen', 'x86/build', 'x86/microcode', 'x86/mm-debug-v2',...

Merge branches 'x86/xen', 'x86/build', 'x86/microcode', 'x86/mm-debug-v2', 'x86/memory-corruption-check', 'x86/early-printk', 'x86/xsave', 'x86/ptrace-v2', 'x86/quirks', 'x86/setup', 'x86/spinlocks' and 'x86/signal' into x86/core-v2

Documentation/kernel-parameters.txt

@@ -658,11 +658,12 @@ and is between 256 and 4096 characters. It is defined in the file
 	earlyprintk=	[X86-32,X86-64,SH,BLACKFIN]
 			earlyprintk=vga
 			earlyprintk=serial[,ttySn[,baudrate]]
+			earlyprintk=dbgp
 
 			Append ",keep" to not disable it when the real console
 			takes over.
 
-			Only vga or serial at a time, not both.
+			Only vga or serial or usb debug port at a time.
 
 			Currently only ttyS0 and ttyS1 are supported.
 
@@ -1231,6 +1232,29 @@ and is between 256 and 4096 characters. It is defined in the file
 			         or
 			         memmap=0x10000$0x18690000
 
+	memory_corruption_check=0/1 [X86]
+			Some BIOSes seem to corrupt the first 64k of
+			memory when doing things like suspend/resume.
+			Setting this option will scan the memory
+			looking for corruption.  Enabling this will
+			both detect corruption and prevent the kernel
+			from using the memory being corrupted.
+			However, its intended as a diagnostic tool; if
+			repeatable BIOS-originated corruption always
+			affects the same memory, you can use memmap=
+			to prevent the kernel from using that memory.
+
+	memory_corruption_check_size=size [X86]
+			By default it checks for corruption in the low
+			64k, making this memory unavailable for normal
+			use.  Use this parameter to scan for
+			corruption in more or less memory.
+
+	memory_corruption_check_period=seconds [X86]
+			By default it checks for corruption every 60
+			seconds.  Use this parameter to check at some
+			other rate.  0 disables periodic checking.
+
 	memtest=	[KNL,X86] Enable memtest
 			Format: <integer>
 			range: 0,4 : pattern number

MAINTAINERS

@@ -390,6 +390,11 @@ L:	iommu@lists.linux-foundation.org
 T:	git://git.kernel.org/pub/scm/linux/kernel/git/joro/linux-2.6-iommu.git
 S:	Supported
 
+AMD MICROCODE UPDATE SUPPORT
+P:      Peter Oruba
+M:      peter.oruba@amd.com
+S:      Supported
+
 AMS (Apple Motion Sensor) DRIVER
 P:	Stelian Pop
 M:	stelian@popies.net

arch/ia64/include/asm/siginfo.h

@@ -113,11 +113,6 @@ typedef struct siginfo {
 #undef NSIGSEGV
 #define NSIGSEGV	3
 
-/*
- * SIGTRAP si_codes
- */
-#define TRAP_BRANCH	(__SI_FAULT|3)	/* process taken branch trap */
-#define TRAP_HWBKPT	(__SI_FAULT|4)	/* hardware breakpoint or watchpoint */
 #undef NSIGTRAP
 #define NSIGTRAP	4
 

arch/powerpc/include/asm/siginfo.h

@@ -15,11 +15,6 @@
 
 #include <asm-generic/siginfo.h>
 
-/*
- * SIGTRAP si_codes
- */
-#define TRAP_BRANCH	(__SI_FAULT|3)	/* process taken branch trap */
-#define TRAP_HWBKPT	(__SI_FAULT|4)	/* hardware breakpoint or watchpoint */
 #undef NSIGTRAP
 #define NSIGTRAP	4
 

arch/x86/Kconfig

@@ -778,23 +778,45 @@ config X86_REBOOTFIXUPS
 	  Say N otherwise.
 
 config MICROCODE
-	tristate "/dev/cpu/microcode - Intel IA32 CPU microcode support"
+	tristate "/dev/cpu/microcode - microcode support"
 	select FW_LOADER
 	---help---
 	  If you say Y here, you will be able to update the microcode on
-	  Intel processors in the IA32 family, e.g. Pentium Pro, Pentium II,
-	  Pentium III, Pentium 4, Xeon etc.  You will obviously need the
-	  actual microcode binary data itself which is not shipped with the
-	  Linux kernel.
+	  certain Intel and AMD processors. The Intel support is for the
+	  IA32 family, e.g. Pentium Pro, Pentium II, Pentium III,
+	  Pentium 4, Xeon etc. The AMD support is for family 0x10 and
+	  0x11 processors, e.g. Opteron, Phenom and Turion 64 Ultra.
+	  You will obviously need the actual microcode binary data itself
+	  which is not shipped with the Linux kernel.
 
-	  For latest news and information on obtaining all the required
-	  ingredients for this driver, check:
-	  <http://www.urbanmyth.org/microcode/>.
+	  This option selects the general module only, you need to select
+	  at least one vendor specific module as well.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called microcode.
 
-config MICROCODE_OLD_INTERFACE
+config MICROCODE_INTEL
+       bool "Intel microcode patch loading support"
+       depends on MICROCODE
+       default MICROCODE
+       select FW_LOADER
+       --help---
+         This options enables microcode patch loading support for Intel
+         processors.
+
+         For latest news and information on obtaining all the required
+         Intel ingredients for this driver, check:
+         <http://www.urbanmyth.org/microcode/>.
+
+config MICROCODE_AMD
+       bool "AMD microcode patch loading support"
+       depends on MICROCODE
+       select FW_LOADER
+       --help---
+         If you select this option, microcode patch loading support for AMD
+	 processors will be enabled.
+
+   config MICROCODE_OLD_INTERFACE
 	def_bool y
 	depends on MICROCODE
 
@@ -1061,6 +1083,56 @@ config HIGHPTE
 	  low memory.  Setting this option will put user-space page table
 	  entries in high memory.
 
+config X86_CHECK_BIOS_CORRUPTION
+        bool "Check for low memory corruption"
+	help
+	 Periodically check for memory corruption in low memory, which
+	 is suspected to be caused by BIOS.  Even when enabled in the
+	 configuration, it is disabled at runtime.  Enable it by
+	 setting "memory_corruption_check=1" on the kernel command
+	 line.  By default it scans the low 64k of memory every 60
+	 seconds; see the memory_corruption_check_size and
+	 memory_corruption_check_period parameters in
+	 Documentation/kernel-parameters.txt to adjust this.
+
+	 When enabled with the default parameters, this option has
+	 almost no overhead, as it reserves a relatively small amount
+	 of memory and scans it infrequently.  It both detects corruption
+	 and prevents it from affecting the running system.
+
+	 It is, however, intended as a diagnostic tool; if repeatable
+	 BIOS-originated corruption always affects the same memory,
+	 you can use memmap= to prevent the kernel from using that
+	 memory.
+
+config X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK
+        bool "Set the default setting of memory_corruption_check"
+	depends on X86_CHECK_BIOS_CORRUPTION
+	default y
+	help
+	 Set whether the default state of memory_corruption_check is
+	 on or off.
+
+config X86_RESERVE_LOW_64K
+        bool "Reserve low 64K of RAM on AMI/Phoenix BIOSen"
+	default y
+	help
+	 Reserve the first 64K of physical RAM on BIOSes that are known
+	 to potentially corrupt that memory range. A numbers of BIOSes are
+	 known to utilize this area during suspend/resume, so it must not
+	 be used by the kernel.
+
+	 Set this to N if you are absolutely sure that you trust the BIOS
+	 to get all its memory reservations and usages right.
+
+	 If you have doubts about the BIOS (e.g. suspend/resume does not
+	 work or there's kernel crashes after certain hardware hotplug
+	 events) and it's not AMI or Phoenix, then you might want to enable
+	 X86_CHECK_BIOS_CORRUPTION=y to allow the kernel to check typical
+	 corruption patterns.
+
+	 Say Y if unsure.
+
 config MATH_EMULATION
 	bool
 	prompt "Math emulation" if X86_32

arch/x86/Kconfig.debug

@@ -43,6 +43,19 @@ config EARLY_PRINTK
 	  with klogd/syslogd or the X server. You should normally N here,
 	  unless you want to debug such a crash.
 
+config EARLY_PRINTK_DBGP
+	bool "Early printk via EHCI debug port"
+	default n
+	depends on EARLY_PRINTK && PCI
+	help
+	  Write kernel log output directly into the EHCI debug port.
+
+	  This is useful 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 you want to debug such a crash. You need usb debug device.
+
 config DEBUG_STACKOVERFLOW
 	bool "Check for stack overflows"
 	depends on DEBUG_KERNEL

arch/x86/Makefile_32.cpu

@@ -45,3 +45,8 @@ cflags-$(CONFIG_MGEODEGX1)	+= -march=pentium-mmx
 # cpu entries
 cflags-$(CONFIG_X86_GENERIC) 	+= $(call tune,generic,$(call tune,i686))
 
+# Bug fix for binutils: this option is required in order to keep
+# binutils from generating NOPL instructions against our will.
+ifneq ($(CONFIG_X86_P6_NOP),y)
+cflags-y			+= $(call cc-option,-Wa$(comma)-mtune=generic32,)
+endif

arch/x86/boot/Makefile

@@ -72,9 +72,7 @@ KBUILD_CFLAGS	:= $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
 KBUILD_CFLAGS +=   $(call cc-option,-m32)
 KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
 
-$(obj)/zImage:  IMAGE_OFFSET := 0x1000
 $(obj)/zImage:  asflags-y := $(SVGA_MODE) $(RAMDISK)
-$(obj)/bzImage: IMAGE_OFFSET := 0x100000
 $(obj)/bzImage: ccflags-y := -D__BIG_KERNEL__
 $(obj)/bzImage: asflags-y := $(SVGA_MODE) $(RAMDISK) -D__BIG_KERNEL__
 $(obj)/bzImage: BUILDFLAGS   := -b
@@ -117,7 +115,7 @@ $(obj)/setup.bin: $(obj)/setup.elf FORCE
 	$(call if_changed,objcopy)
 
 $(obj)/compressed/vmlinux: FORCE
-	$(Q)$(MAKE) $(build)=$(obj)/compressed IMAGE_OFFSET=$(IMAGE_OFFSET) $@
+	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
 
 # Set this if you want to pass append arguments to the zdisk/fdimage/isoimage kernel
 FDARGS =
@@ -181,6 +179,7 @@ isoimage: $(BOOTIMAGE)
 	mkisofs -J -r -o $(obj)/image.iso -b isolinux.bin -c boot.cat \
 		-no-emul-boot -boot-load-size 4 -boot-info-table \
 		$(obj)/isoimage
+	isohybrid $(obj)/image.iso 2>/dev/null || true
 	rm -rf $(obj)/isoimage
 
 zlilo: $(BOOTIMAGE)

arch/x86/boot/compressed/Makefile

@@ -27,9 +27,8 @@ $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
 
-ifeq ($(CONFIG_X86_32),y)
-targets += vmlinux.bin.all vmlinux.relocs
-hostprogs-y := relocs
+targets += vmlinux.bin.all vmlinux.relocs relocs
+hostprogs-$(CONFIG_X86_32) += relocs
 
 quiet_cmd_relocs = RELOCS  $@
       cmd_relocs = $(obj)/relocs $< > $@;$(obj)/relocs --abs-relocs $<
@@ -43,6 +42,8 @@ quiet_cmd_relocbin = BUILD   $@
 $(obj)/vmlinux.bin.all: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,relocbin)
 
+ifeq ($(CONFIG_X86_32),y)
+
 ifdef CONFIG_RELOCATABLE
 $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin.all FORCE
 	$(call if_changed,gzip)
@@ -59,6 +60,5 @@ $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
 LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T
 endif
 
-
 $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.gz FORCE
 	$(call if_changed,ld)

arch/x86/boot/edd.c

@@ -41,6 +41,7 @@ static u32 read_mbr_sig(u8 devno, struct edd_info *ei, u32 *mbrsig)
 	char *mbrbuf_ptr, *mbrbuf_end;
 	u32 buf_base, mbr_base;
 	extern char _end[];
+	u16 mbr_magic;
 
 	sector_size = ei->params.bytes_per_sector;
 	if (!sector_size)
@@ -58,11 +59,15 @@ static u32 read_mbr_sig(u8 devno, struct edd_info *ei, u32 *mbrsig)
 	if (mbrbuf_end > (char *)(size_t)boot_params.hdr.heap_end_ptr)
 		return -1;
 
+	memset(mbrbuf_ptr, 0, sector_size);
 	if (read_mbr(devno, mbrbuf_ptr))
 		return -1;
 
 	*mbrsig = *(u32 *)&mbrbuf_ptr[EDD_MBR_SIG_OFFSET];
-	return 0;
+	mbr_magic = *(u16 *)&mbrbuf_ptr[510];
+
+	/* check for valid MBR magic */
+	return mbr_magic == 0xAA55 ? 0 : -1;
 }
 
 static int get_edd_info(u8 devno, struct edd_info *ei)

arch/x86/boot/video-vesa.c

@@ -224,7 +224,7 @@ static void vesa_store_pm_info(void)
 static void vesa_store_mode_params_graphics(void)
 {
 	/* Tell the kernel we're in VESA graphics mode */
-	boot_params.screen_info.orig_video_isVGA = 0x23;
+	boot_params.screen_info.orig_video_isVGA = VIDEO_TYPE_VLFB;
 
 	/* Mode parameters */
 	boot_params.screen_info.vesa_attributes = vminfo.mode_attr;

arch/x86/configs/i386_defconfig

@@ -1535,7 +1535,6 @@ CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_VGA_CONSOLE=y
 CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=64
-CONFIG_VIDEO_SELECT=y
 CONFIG_DUMMY_CONSOLE=y
 # CONFIG_FRAMEBUFFER_CONSOLE is not set
 CONFIG_LOGO=y

arch/x86/configs/x86_64_defconfig

@@ -1505,7 +1505,6 @@ CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_VGA_CONSOLE=y
 CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=64
-CONFIG_VIDEO_SELECT=y
 CONFIG_DUMMY_CONSOLE=y
 # CONFIG_FRAMEBUFFER_CONSOLE is not set
 CONFIG_LOGO=y

arch/x86/ia32/ia32_signal.c

@@ -351,31 +351,28 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
 	savesegment(es, tmp);
 	err |= __put_user(tmp, (unsigned int __user *)&sc->es);
 
-	err |= __put_user((u32)regs->di, &sc->di);
-	err |= __put_user((u32)regs->si, &sc->si);
-	err |= __put_user((u32)regs->bp, &sc->bp);
-	err |= __put_user((u32)regs->sp, &sc->sp);
-	err |= __put_user((u32)regs->bx, &sc->bx);
-	err |= __put_user((u32)regs->dx, &sc->dx);
-	err |= __put_user((u32)regs->cx, &sc->cx);
-	err |= __put_user((u32)regs->ax, &sc->ax);
-	err |= __put_user((u32)regs->cs, &sc->cs);
-	err |= __put_user((u32)regs->ss, &sc->ss);
+	err |= __put_user(regs->di, &sc->di);
+	err |= __put_user(regs->si, &sc->si);
+	err |= __put_user(regs->bp, &sc->bp);
+	err |= __put_user(regs->sp, &sc->sp);
+	err |= __put_user(regs->bx, &sc->bx);
+	err |= __put_user(regs->dx, &sc->dx);
+	err |= __put_user(regs->cx, &sc->cx);
+	err |= __put_user(regs->ax, &sc->ax);
+	err |= __put_user(regs->cs, &sc->cs);
+	err |= __put_user(regs->ss, &sc->ss);
 	err |= __put_user(current->thread.trap_no, &sc->trapno);
 	err |= __put_user(current->thread.error_code, &sc->err);
-	err |= __put_user((u32)regs->ip, &sc->ip);
-	err |= __put_user((u32)regs->flags, &sc->flags);
-	err |= __put_user((u32)regs->sp, &sc->sp_at_signal);
+	err |= __put_user(regs->ip, &sc->ip);
+	err |= __put_user(regs->flags, &sc->flags);
+	err |= __put_user(regs->sp, &sc->sp_at_signal);
 
 	tmp = save_i387_xstate_ia32(fpstate);
 	if (tmp < 0)
 		err = -EFAULT;
-	else {
-		clear_used_math();
-		stts();
+	else
 		err |= __put_user(ptr_to_compat(tmp ? fpstate : NULL),
 					&sc->fpstate);
-	}
 
 	/* non-iBCS2 extensions.. */
 	err |= __put_user(mask, &sc->oldmask);
@@ -444,21 +441,18 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
-		goto give_sigsegv;
+		return -EFAULT;
 
-	err |= __put_user(sig, &frame->sig);
-	if (err)
-		goto give_sigsegv;
+	if (__put_user(sig, &frame->sig))
+		return -EFAULT;
 
-	err |= ia32_setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0]);
-	if (err)
-		goto give_sigsegv;
+	if (ia32_setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0]))
+		return -EFAULT;
 
 	if (_COMPAT_NSIG_WORDS > 1) {
-		err |= __copy_to_user(frame->extramask, &set->sig[1],
-				      sizeof(frame->extramask));
-		if (err)
-			goto give_sigsegv;
+		if (__copy_to_user(frame->extramask, &set->sig[1],
+				   sizeof(frame->extramask)))
+			return -EFAULT;
 	}
 
 	if (ka->sa.sa_flags & SA_RESTORER) {
@@ -479,7 +473,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 	 */
 	err |= __copy_to_user(frame->retcode, &code, 8);
 	if (err)
-		goto give_sigsegv;
+		return -EFAULT;
 
 	/* Set up registers for signal handler */
 	regs->sp = (unsigned long) frame;
@@ -502,10 +496,6 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 #endif
 
 	return 0;
-
-give_sigsegv:
-	force_sigsegv(sig, current);
-	return -EFAULT;
 }
 
 int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
@@ -533,14 +523,14 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
-		goto give_sigsegv;
+		return -EFAULT;
 
 	err |= __put_user(sig, &frame->sig);
 	err |= __put_user(ptr_to_compat(&frame->info), &frame->pinfo);
 	err |= __put_user(ptr_to_compat(&frame->uc), &frame->puc);
 	err |= copy_siginfo_to_user32(&frame->info, info);
 	if (err)
-		goto give_sigsegv;
+		return -EFAULT;
 
 	/* Create the ucontext.  */
 	if (cpu_has_xsave)
@@ -556,7 +546,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 				     regs, set->sig[0]);
 	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
 	if (err)
-		goto give_sigsegv;
+		return -EFAULT;
 
 	if (ka->sa.sa_flags & SA_RESTORER)
 		restorer = ka->sa.sa_restorer;
@@ -571,7 +561,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	 */
 	err |= __copy_to_user(frame->retcode, &code, 8);
 	if (err)
-		goto give_sigsegv;
+		return -EFAULT;
 
 	/* Set up registers for signal handler */
 	regs->sp = (unsigned long) frame;
@@ -599,8 +589,4 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 #endif
 
 	return 0;
-
-give_sigsegv:
-	force_sigsegv(sig, current);
-	return -EFAULT;
 }

arch/x86/kernel/Makefile

@@ -10,7 +10,7 @@ ifdef CONFIG_FTRACE
 # Do not profile debug and lowlevel utilities
 CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
-CFLAGS_REMOVE_paravirt.o = -pg
+CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 endif
 
 #
@@ -51,7 +51,6 @@ obj-$(CONFIG_X86_BIOS_REBOOT)	+= reboot.o
 obj-$(CONFIG_MCA)		+= mca_32.o
 obj-$(CONFIG_X86_MSR)		+= msr.o
 obj-$(CONFIG_X86_CPUID)		+= cpuid.o
-obj-$(CONFIG_MICROCODE)		+= microcode.o
 obj-$(CONFIG_PCI)		+= early-quirks.o
 apm-y				:= apm_32.o
 obj-$(CONFIG_APM)		+= apm.o
@@ -90,7 +89,7 @@ obj-$(CONFIG_DEBUG_NX_TEST)	+= test_nx.o
 obj-$(CONFIG_VMI)		+= vmi_32.o vmiclock_32.o
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o
 obj-$(CONFIG_KVM_CLOCK)		+= kvmclock.o
-obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch_$(BITS).o
+obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch_$(BITS).o paravirt-spinlocks.o
 obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
 
 obj-$(CONFIG_PCSPKR_PLATFORM)	+= pcspeaker.o
@@ -100,6 +99,11 @@ scx200-y			+= scx200_32.o
 
 obj-$(CONFIG_OLPC)		+= olpc.o
 
+microcode-y				:= microcode_core.o
+microcode-$(CONFIG_MICROCODE_INTEL)	+= microcode_intel.o
+microcode-$(CONFIG_MICROCODE_AMD)	+= microcode_amd.o
+obj-$(CONFIG_MICROCODE)			+= microcode.o
+
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)

arch/x86/kernel/acpi/boot.c

@@ -1418,8 +1418,16 @@ static int __init force_acpi_ht(const struct dmi_system_id *d)
  */
 static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d)
 {
-	pr_notice("%s detected: Ignoring BIOS IRQ0 pin2 override\n", d->ident);
+	/*
+	 * The ati_ixp4x0_rev() early PCI quirk should have set
+	 * the acpi_skip_timer_override flag already:
+	 */
+	if (!acpi_skip_timer_override) {
+		WARN(1, KERN_ERR "ati_ixp4x0 quirk not complete.\n");
+		pr_notice("%s detected: Ignoring BIOS IRQ0 pin2 override\n",
+			d->ident);
 		acpi_skip_timer_override = 1;
+	}
 	return 0;
 }
 

arch/x86/kernel/cpu/common.c

@@ -1121,16 +1121,5 @@ void __cpuinit cpu_init(void)
 	xsave_init();
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-void __cpuinit cpu_uninit(void)
-{
-	int cpu = raw_smp_processor_id();
-	cpu_clear(cpu, cpu_initialized);
-
-	/* lazy TLB state */
-	per_cpu(cpu_tlbstate, cpu).state = 0;
-	per_cpu(cpu_tlbstate, cpu).active_mm = &init_mm;
-}
-#endif
 
 #endif

arch/x86/kernel/doublefault_32.c

@@ -66,6 +66,6 @@ struct tss_struct doublefault_tss __cacheline_aligned = {
 		.ds		= __USER_DS,
 		.fs		= __KERNEL_PERCPU,
 
-		.__cr3		= __pa(swapper_pg_dir)
+		.__cr3		= __phys_addr_const((unsigned long)swapper_pg_dir)
 	}
 };

arch/x86/kernel/early-quirks.c

@@ -95,6 +95,52 @@ static void __init nvidia_bugs(int num, int slot, int func)
 
 }
 
+static u32 ati_ixp4x0_rev(int num, int slot, int func)
+{
+	u32 d;
+	u8  b;
+
+	b = read_pci_config_byte(num, slot, func, 0xac);
+	b &= ~(1<<5);
+	write_pci_config_byte(num, slot, func, 0xac, b);
+
+	d = read_pci_config(num, slot, func, 0x70);
+	d |= 1<<8;
+	write_pci_config(num, slot, func, 0x70, d);
+
+	d = read_pci_config(num, slot, func, 0x8);
+	d &= 0xff;
+	return d;
+}
+
+static void __init ati_bugs(int num, int slot, int func)
+{
+#if defined(CONFIG_ACPI) && defined (CONFIG_X86_IO_APIC)
+	u32 d;
+	u8  b;
+
+	if (acpi_use_timer_override)
+		return;
+
+	d = ati_ixp4x0_rev(num, slot, func);
+	if (d  < 0x82)
+		acpi_skip_timer_override = 1;
+	else {
+		/* check for IRQ0 interrupt swap */
+		outb(0x72, 0xcd6); b = inb(0xcd7);
+		if (!(b & 0x2))
+			acpi_skip_timer_override = 1;
+	}
+
+	if (acpi_skip_timer_override) {
+		printk(KERN_INFO "SB4X0 revision 0x%x\n", d);
+		printk(KERN_INFO "Ignoring ACPI timer override.\n");
+		printk(KERN_INFO "If you got timer trouble "
+		       "try acpi_use_timer_override\n");
+	}
+#endif
+}
+
 #ifdef CONFIG_DMAR
 static void __init intel_g33_dmar(int num, int slot, int func)
 {
@@ -128,6 +174,8 @@ static struct chipset early_qrk[] __initdata = {
 	  PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, via_bugs },
 	{ PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB,
 	  PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, fix_hypertransport_config },
+	{ PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP400_SMBUS,
+	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs },
 #ifdef CONFIG_DMAR
 	{ PCI_VENDOR_ID_INTEL, 0x29c0,
 	  PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, intel_g33_dmar },

arch/x86/kernel/i387.c

@@ -468,9 +468,23 @@ static int save_i387_fxsave(struct _fpstate_ia32 __user *buf)
 
 static int save_i387_xsave(void __user *buf)
 {
+	struct task_struct *tsk = current;
 	struct _fpstate_ia32 __user *fx = buf;
 	int err = 0;
 
+	/*
+	 * For legacy compatible, we always set FP/SSE bits in the bit
+	 * vector while saving the state to the user context.
+	 * This will enable us capturing any changes(during sigreturn) to
+	 * the FP/SSE bits by the legacy applications which don't touch
+	 * xstate_bv in the xsave header.
+	 *
+	 * xsave aware applications can change the xstate_bv in the xsave
+	 * header as well as change any contents in the memory layout.
+	 * xrestore as part of sigreturn will capture all the changes.
+	 */
+	tsk->thread.xstate->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
+
 	if (save_i387_fxsave(fx) < 0)
 		return -1;
 

arch/x86/kernel/ldt.c

@@ -52,6 +52,8 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
 	memset(newldt + oldsize * LDT_ENTRY_SIZE, 0,
 	       (mincount - oldsize) * LDT_ENTRY_SIZE);
 
+	paravirt_alloc_ldt(newldt, mincount);
+
 #ifdef CONFIG_X86_64
 	/* CHECKME: Do we really need this ? */
 	wmb();
@@ -74,6 +76,7 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
 #endif
 	}
 	if (oldsize) {
+		paravirt_free_ldt(oldldt, oldsize);
 		if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE)
 			vfree(oldldt);
 		else
@@ -85,10 +88,13 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
 static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
 {
 	int err = alloc_ldt(new, old->size, 0);
+	int i;
 
 	if (err < 0)
 		return err;
-	memcpy(new->ldt, old->ldt, old->size * LDT_ENTRY_SIZE);
+
+	for(i = 0; i < old->size; i++)
+		write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE);
 	return 0;
 }
 
@@ -125,6 +131,7 @@ void destroy_context(struct mm_struct *mm)
 		if (mm == current->active_mm)
 			clear_LDT();
 #endif
+		paravirt_free_ldt(mm->context.ldt, mm->context.size);
 		if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE)
 			vfree(mm->context.ldt);
 		else

arch/x86/kernel/paravirt-spinlocks.c

+/*
+ * Split spinlock implementation out into its own file, so it can be
+ * compiled in a FTRACE-compatible way.
+ */
+#include <linux/spinlock.h>
+#include <linux/module.h>
+
+#include <asm/paravirt.h>
+
+static void default_spin_lock_flags(struct raw_spinlock *lock, unsigned long flags)
+{
+	__raw_spin_lock(lock);
+}
+
+struct pv_lock_ops pv_lock_ops = {
+#ifdef CONFIG_SMP
+	.spin_is_locked = __ticket_spin_is_locked,
+	.spin_is_contended = __ticket_spin_is_contended,
+
+	.spin_lock = __ticket_spin_lock,
+	.spin_lock_flags = default_spin_lock_flags,
+	.spin_trylock = __ticket_spin_trylock,
+	.spin_unlock = __ticket_spin_unlock,
+#endif
+};
+EXPORT_SYMBOL(pv_lock_ops);
+
+void __init paravirt_use_bytelocks(void)
+{
+#ifdef CONFIG_SMP
+	pv_lock_ops.spin_is_locked = __byte_spin_is_locked;
+	pv_lock_ops.spin_is_contended = __byte_spin_is_contended;
+	pv_lock_ops.spin_lock = __byte_spin_lock;
+	pv_lock_ops.spin_trylock = __byte_spin_trylock;
+	pv_lock_ops.spin_unlock = __byte_spin_unlock;
+#endif
+}

arch/x86/kernel/paravirt.c

@@ -268,17 +268,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 	return __get_cpu_var(paravirt_lazy_mode);
 }
 
-void __init paravirt_use_bytelocks(void)
-{
-#ifdef CONFIG_SMP
-	pv_lock_ops.spin_is_locked = __byte_spin_is_locked;
-	pv_lock_ops.spin_is_contended = __byte_spin_is_contended;
-	pv_lock_ops.spin_lock = __byte_spin_lock;
-	pv_lock_ops.spin_trylock = __byte_spin_trylock;
-	pv_lock_ops.spin_unlock = __byte_spin_unlock;
-#endif
-}
-
 struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -349,6 +338,10 @@ struct pv_cpu_ops pv_cpu_ops = {
 	.write_ldt_entry = native_write_ldt_entry,
 	.write_gdt_entry = native_write_gdt_entry,
 	.write_idt_entry = native_write_idt_entry,
+
+	.alloc_ldt = paravirt_nop,
+	.free_ldt = paravirt_nop,
+
 	.load_sp0 = native_load_sp0,
 
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
@@ -460,18 +453,6 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.set_fixmap = native_set_fixmap,
 };
 
-struct pv_lock_ops pv_lock_ops = {
-#ifdef CONFIG_SMP
-	.spin_is_locked = __ticket_spin_is_locked,
-	.spin_is_contended = __ticket_spin_is_contended,
-
-	.spin_lock = __ticket_spin_lock,
-	.spin_trylock = __ticket_spin_trylock,
-	.spin_unlock = __ticket_spin_unlock,
-#endif
-};
-EXPORT_SYMBOL(pv_lock_ops);
-
 EXPORT_SYMBOL_GPL(pv_time_ops);
 EXPORT_SYMBOL    (pv_cpu_ops);
 EXPORT_SYMBOL    (pv_mmu_ops);

arch/x86/kernel/process_32.c

@@ -76,47 +76,12 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 	return ((unsigned long *)tsk->thread.sp)[3];
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-#include <asm/nmi.h>
-
-static void cpu_exit_clear(void)
-{
-	int cpu = raw_smp_processor_id();
-
-	idle_task_exit();
-
-	cpu_uninit();
-	irq_ctx_exit(cpu);
-
-	cpu_clear(cpu, cpu_callout_map);
-	cpu_clear(cpu, cpu_callin_map);
-
-	numa_remove_cpu(cpu);
-	c1e_remove_cpu(cpu);
-}
-
-/* We don't actually take CPU down, just spin without interrupts. */
-static inline void play_dead(void)
-{
-	/* This must be done before dead CPU ack */
-	cpu_exit_clear();
-	mb();
-	/* Ack it */
-	__get_cpu_var(cpu_state) = CPU_DEAD;
-
-	/*
-	 * With physical CPU hotplug, we should halt the cpu
-	 */
-	local_irq_disable();
-	/* mask all interrupts, flush any and all caches, and halt */
-	wbinvd_halt();
-}
-#else
+#ifndef CONFIG_SMP
 static inline void play_dead(void)
 {
 	BUG();
 }
-#endif /* CONFIG_HOTPLUG_CPU */
+#endif
 
 /*
  * The idle thread. There's no useful work to be

arch/x86/kernel/process_64.c

@@ -86,30 +86,12 @@ void exit_idle(void)
 	__exit_idle();
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-DECLARE_PER_CPU(int, cpu_state);
-
-#include <linux/nmi.h>
-/* We halt the CPU with physical CPU hotplug */
-static inline void play_dead(void)
-{
-	idle_task_exit();
-	c1e_remove_cpu(raw_smp_processor_id());
-
-	mb();
-	/* Ack it */
-	__get_cpu_var(cpu_state) = CPU_DEAD;
-
-	local_irq_disable();
-	/* mask all interrupts, flush any and all caches, and halt */
-	wbinvd_halt();
-}
-#else
+#ifndef CONFIG_SMP
 static inline void play_dead(void)
 {
 	BUG();
 }
-#endif /* CONFIG_HOTPLUG_CPU */
+#endif
 
 /*
  * The idle thread. There's no useful work to be

arch/x86/kernel/ptrace.c

@@ -40,7 +40,9 @@ enum x86_regset {
 	REGSET_GENERAL,
 	REGSET_FP,
 	REGSET_XFP,
+	REGSET_IOPERM64 = REGSET_XFP,
 	REGSET_TLS,
+	REGSET_IOPERM32,
 };
 
 /*
@@ -555,6 +557,29 @@ static int ptrace_set_debugreg(struct task_struct *child,
 	return 0;
 }
 
+/*
+ * These access the current or another (stopped) task's io permission
+ * bitmap for debugging or core dump.
+ */
+static int ioperm_active(struct task_struct *target,
+			 const struct user_regset *regset)
+{
+	return target->thread.io_bitmap_max / regset->size;
+}
+
+static int ioperm_get(struct task_struct *target,
+		      const struct user_regset *regset,
+		      unsigned int pos, unsigned int count,
+		      void *kbuf, void __user *ubuf)
+{
+	if (!target->thread.io_bitmap_ptr)
+		return -ENXIO;
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   target->thread.io_bitmap_ptr,
+				   0, IO_BITMAP_BYTES);
+}
+
 #ifdef CONFIG_X86_PTRACE_BTS
 /*
  * The configuration for a particular BTS hardware implementation.
@@ -1385,6 +1410,12 @@ static const struct user_regset x86_64_regsets[] = {
 		.size = sizeof(long), .align = sizeof(long),
 		.active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
 	},
+	[REGSET_IOPERM64] = {
+		.core_note_type = NT_386_IOPERM,
+		.n = IO_BITMAP_LONGS,
+		.size = sizeof(long), .align = sizeof(long),
+		.active = ioperm_active, .get = ioperm_get
+	},
 };
 
 static const struct user_regset_view user_x86_64_view = {
@@ -1431,6 +1462,12 @@ static const struct user_regset x86_32_regsets[] = {
 		.active = regset_tls_active,
 		.get = regset_tls_get, .set = regset_tls_set
 	},
+	[REGSET_IOPERM32] = {
+		.core_note_type = NT_386_IOPERM,
+		.n = IO_BITMAP_BYTES / sizeof(u32),
+		.size = sizeof(u32), .align = sizeof(u32),
+		.active = ioperm_active, .get = ioperm_get
+	},
 };
 
 static const struct user_regset_view user_x86_32_view = {
@@ -1452,7 +1489,8 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 #endif
 }
 
-void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
+void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
+					 int error_code, int si_code)
 {
 	struct siginfo info;
 
@@ -1461,7 +1499,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
 
 	memset(&info, 0, sizeof(info));
 	info.si_signo = SIGTRAP;
-	info.si_code = TRAP_BRKPT;
+	info.si_code = si_code;
 
 	/* User-mode ip? */
 	info.si_addr = user_mode_vm(regs) ? (void __user *) regs->ip : NULL;
@@ -1548,5 +1586,5 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs)
 	 */
 	if (test_thread_flag(TIF_SINGLESTEP) &&
 	    tracehook_consider_fatal_signal(current, SIGTRAP, SIG_DFL))
-		send_sigtrap(current, regs, 0);
+		send_sigtrap(current, regs, 0, TRAP_BRKPT);
 }

arch/x86/kernel/setup.c

@@ -581,6 +581,190 @@ static struct x86_quirks default_x86_quirks __initdata;
 
 struct x86_quirks *x86_quirks __initdata = &default_x86_quirks;
 
+/*
+ * Some BIOSes seem to corrupt the low 64k of memory during events
+ * like suspend/resume and unplugging an HDMI cable.  Reserve all
+ * remaining free memory in that area and fill it with a distinct
+ * pattern.
+ */
+#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
+#define MAX_SCAN_AREAS	8
+
+static int __read_mostly memory_corruption_check = -1;
+
+static unsigned __read_mostly corruption_check_size = 64*1024;
+static unsigned __read_mostly corruption_check_period = 60; /* seconds */
+
+static struct e820entry scan_areas[MAX_SCAN_AREAS];
+static int num_scan_areas;
+
+
+static int set_corruption_check(char *arg)
+{
+	char *end;
+
+	memory_corruption_check = simple_strtol(arg, &end, 10);
+
+	return (*end == 0) ? 0 : -EINVAL;
+}
+early_param("memory_corruption_check", set_corruption_check);
+
+static int set_corruption_check_period(char *arg)
+{
+	char *end;
+
+	corruption_check_period = simple_strtoul(arg, &end, 10);
+
+	return (*end == 0) ? 0 : -EINVAL;
+}
+early_param("memory_corruption_check_period", set_corruption_check_period);
+
+static int set_corruption_check_size(char *arg)
+{
+	char *end;
+	unsigned size;
+
+	size = memparse(arg, &end);
+
+	if (*end == '\0')
+		corruption_check_size = size;
+
+	return (size == corruption_check_size) ? 0 : -EINVAL;
+}
+early_param("memory_corruption_check_size", set_corruption_check_size);
+
+
+static void __init setup_bios_corruption_check(void)
+{
+	u64 addr = PAGE_SIZE;	/* assume first page is reserved anyway */
+
+	if (memory_corruption_check == -1) {
+		memory_corruption_check =
+#ifdef CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK
+			1
+#else
+			0
+#endif
+			;
+	}
+
+	if (corruption_check_size == 0)
+		memory_corruption_check = 0;
+
+	if (!memory_corruption_check)
+		return;
+
+	corruption_check_size = round_up(corruption_check_size, PAGE_SIZE);
+
+	while(addr < corruption_check_size && num_scan_areas < MAX_SCAN_AREAS) {
+		u64 size;
+		addr = find_e820_area_size(addr, &size, PAGE_SIZE);
+
+		if (addr == 0)
+			break;
+
+		if ((addr + size) > corruption_check_size)
+			size = corruption_check_size - addr;
+
+		if (size == 0)
+			break;
+
+		e820_update_range(addr, size, E820_RAM, E820_RESERVED);
+		scan_areas[num_scan_areas].addr = addr;
+		scan_areas[num_scan_areas].size = size;
+		num_scan_areas++;
+
+		/* Assume we've already mapped this early memory */
+		memset(__va(addr), 0, size);
+
+		addr += size;
+	}
+
+	printk(KERN_INFO "Scanning %d areas for low memory corruption\n",
+	       num_scan_areas);
+	update_e820();
+}
+
+static struct timer_list periodic_check_timer;
+
+void check_for_bios_corruption(void)
+{
+	int i;
+	int corruption = 0;
+
+	if (!memory_corruption_check)
+		return;
+
+	for(i = 0; i < num_scan_areas; i++) {
+		unsigned long *addr = __va(scan_areas[i].addr);
+		unsigned long size = scan_areas[i].size;
+
+		for(; size; addr++, size -= sizeof(unsigned long)) {
+			if (!*addr)
+				continue;
+			printk(KERN_ERR "Corrupted low memory at %p (%lx phys) = %08lx\n",
+			       addr, __pa(addr), *addr);
+			corruption = 1;
+			*addr = 0;
+		}
+	}
+
+	WARN(corruption, KERN_ERR "Memory corruption detected in low memory\n");
+}
+
+static void periodic_check_for_corruption(unsigned long data)
+{
+	check_for_bios_corruption();
+	mod_timer(&periodic_check_timer, round_jiffies(jiffies + corruption_check_period*HZ));
+}
+
+void start_periodic_check_for_corruption(void)
+{
+	if (!memory_corruption_check || corruption_check_period == 0)
+		return;
+
+	printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n",
+	       corruption_check_period);
+
+	init_timer(&periodic_check_timer);
+	periodic_check_timer.function = &periodic_check_for_corruption;
+	periodic_check_for_corruption(0);
+}
+#endif
+
+static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
+{
+	printk(KERN_NOTICE
+		"%s detected: BIOS may corrupt low RAM, working it around.\n",
+		d->ident);
+
+	e820_update_range(0, 0x10000, E820_RAM, E820_RESERVED);
+	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+
+	return 0;
+}
+
+/* List of systems that have known low memory corruption BIOS problems */
+static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
+#ifdef CONFIG_X86_RESERVE_LOW_64K
+	{
+		.callback = dmi_low_memory_corruption,
+		.ident = "AMI BIOS",
+		.matches = {
+			DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."),
+		},
+	},
+	{
+		.callback = dmi_low_memory_corruption,
+		.ident = "Phoenix BIOS",
+		.matches = {
+			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+		},
+	},
+#endif
+	{}
+};
+
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
@@ -715,6 +899,10 @@ void __init setup_arch(char **cmdline_p)
 
 	finish_e820_parsing();
 
+	dmi_scan_machine();
+
+	dmi_check_system(bad_bios_dmi_table);
+
 #ifdef CONFIG_X86_32
 	probe_roms();
 #endif
@@ -771,6 +959,10 @@ void __init setup_arch(char **cmdline_p)
 	high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
 #endif
 
+#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
+	setup_bios_corruption_check();
+#endif
+
 	/* max_pfn_mapped is updated here */
 	max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
 	max_pfn_mapped = max_low_pfn_mapped;
@@ -799,8 +991,6 @@ void __init setup_arch(char **cmdline_p)
 	vsmp_init();
 #endif
 
-	dmi_scan_machine();
-
 	io_delay_init();
 
 	/*
@@ -903,3 +1093,5 @@ void __init setup_arch(char **cmdline_p)
 #endif
 #endif
 }
+
+

arch/x86/kernel/signal_64.c

@@ -52,6 +52,16 @@ sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
 	return do_sigaltstack(uss, uoss, regs->sp);
 }
 
+#define COPY(x)			{		\
+	err |= __get_user(regs->x, &sc->x);	\
+}
+
+#define COPY_SEG_STRICT(seg)	{			\
+		unsigned short tmp;			\
+		err |= __get_user(tmp, &sc->seg);	\
+		regs->seg = tmp | 3;			\
+}
+
 /*
  * Do a signal return; undo the signal stack.
  */
@@ -59,13 +69,13 @@ static int
 restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 		   unsigned long *pax)
 {
+	void __user *buf;
+	unsigned int tmpflags;
 	unsigned int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
 	current_thread_info()->restart_block.fn = do_no_restart_syscall;
 
-#define COPY(x)		(err |= __get_user(regs->x, &sc->x))
-
 	COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
 	COPY(dx); COPY(cx); COPY(ip);
 	COPY(r8);
@@ -80,34 +90,24 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	/* Kernel saves and restores only the CS segment register on signals,
 	 * which is the bare minimum needed to allow mixed 32/64-bit code.
 	 * App's signal handler can save/restore other segments if needed. */
-	{
-		unsigned cs;
-		err |= __get_user(cs, &sc->cs);
-		regs->cs = cs | 3;	/* Force into user mode */
-	}
+	COPY_SEG_STRICT(cs);
 
-	{
-		unsigned int tmpflags;
 	err |= __get_user(tmpflags, &sc->flags);
 	regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
 	regs->orig_ax = -1;		/* disable syscall checks */
-	}
 
-	{
-		struct _fpstate __user *buf;
 	err |= __get_user(buf, &sc->fpstate);
 	err |= restore_i387_xstate(buf);
-	}
 
 	err |= __get_user(*pax, &sc->ax);
 	return err;
 }
 
-asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
+static long do_rt_sigreturn(struct pt_regs *regs)
 {
 	struct rt_sigframe __user *frame;
-	sigset_t set;
 	unsigned long ax;
+	sigset_t set;
 
 	frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
@@ -130,10 +130,15 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
 	return ax;
 
 badframe:
-	signal_fault(regs, frame, "sigreturn");
+	signal_fault(regs, frame, "rt_sigreturn");
 	return 0;
 }
 
+asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
+{
+	return do_rt_sigreturn(regs);
+}
+
 /*
  * Set up a signal frame.
  */
@@ -195,7 +200,7 @@ get_stack(struct k_sigaction *ka, struct pt_regs *regs, unsigned long size)
 	return (void __user *)round_down(sp - size, 64);
 }
 
-static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 			    sigset_t *set, struct pt_regs *regs)
 {
 	struct rt_sigframe __user *frame;
@@ -209,17 +214,16 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 			(unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8;
 
 		if (save_i387_xstate(fp) < 0)
-			err |= -1;
+			return -EFAULT;
 	} else
 		frame = get_stack(ka, regs, sizeof(struct rt_sigframe)) - 8;
 
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
-		goto give_sigsegv;
+		return -EFAULT;
 
 	if (ka->sa.sa_flags & SA_SIGINFO) {
-		err |= copy_siginfo_to_user(&frame->info, info);
-		if (err)
-			goto give_sigsegv;
+		if (copy_siginfo_to_user(&frame->info, info))
+			return -EFAULT;
 	}
 
 	/* Create the ucontext.  */
@@ -247,11 +251,11 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
 	} else {
 		/* could use a vstub here */
-		goto give_sigsegv;
+		return -EFAULT;
 	}
 
 	if (err)
-		goto give_sigsegv;
+		return -EFAULT;
 
 	/* Set up registers for signal handler */
 	regs->di = sig;
@@ -271,15 +275,45 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	regs->cs = __USER_CS;
 
 	return 0;
-
-give_sigsegv:
-	force_sigsegv(sig, current);
-	return -EFAULT;
 }
 
 /*
  * OK, we're invoking a handler
  */
+static int signr_convert(int sig)
+{
+	return sig;
+}
+
+#ifdef CONFIG_IA32_EMULATION
+#define is_ia32	test_thread_flag(TIF_IA32)
+#else
+#define is_ia32	0
+#endif
+
+static int
+setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+	       sigset_t *set, struct pt_regs *regs)
+{
+	int usig = signr_convert(sig);
+	int ret;
+
+	/* Set up the stack frame */
+	if (is_ia32) {
+		if (ka->sa.sa_flags & SA_SIGINFO)
+			ret = ia32_setup_rt_frame(usig, ka, info, set, regs);
+		else
+			ret = ia32_setup_frame(usig, ka, set, regs);
+	} else
+		ret = __setup_rt_frame(sig, ka, info, set, regs);
+
+	if (ret) {
+		force_sigsegv(sig, current);
+		return -EFAULT;
+	}
+
+	return ret;
+}
 
 static int
 handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
@@ -317,23 +351,19 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
 	    likely(test_and_clear_thread_flag(TIF_FORCED_TF)))
 		regs->flags &= ~X86_EFLAGS_TF;
 
-#ifdef CONFIG_IA32_EMULATION
-	if (test_thread_flag(TIF_IA32)) {
-		if (ka->sa.sa_flags & SA_SIGINFO)
-			ret = ia32_setup_rt_frame(sig, ka, info, oldset, regs);
-		else
-			ret = ia32_setup_frame(sig, ka, oldset, regs);
-	} else
-#endif
 	ret = setup_rt_frame(sig, ka, info, oldset, regs);
 
-	if (ret == 0) {
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_X86_64
 	/*
 	 * This has nothing to do with segment registers,
 	 * despite the name.  This magic affects uaccess.h
 	 * macros' behavior.  Reset it to the normal setting.
 	 */
 	set_fs(USER_DS);
+#endif
 
 	/*
 	 * Clear the direction flag as per the ABI for function entry.
@@ -357,11 +387,12 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
 
 	tracehook_signal_handler(sig, info, ka, regs,
 				 test_thread_flag(TIF_SINGLESTEP));
-	}
 
-	return ret;
+	return 0;
 }
 
+#define NR_restart_syscall	\
+	test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall
 /*
  * Note that 'init' is a special process: it doesn't get signals it doesn't
  * want to handle. Thus you cannot kill init even with a SIGKILL even by
@@ -391,7 +422,8 @@ static void do_signal(struct pt_regs *regs)
 
 	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 	if (signr > 0) {
-		/* Re-enable any watchpoints before delivering the
+		/*
+		 * Re-enable any watchpoints before delivering the
 		 * signal to user space. The processor register will
 		 * have been cleared if the watchpoint triggered
 		 * inside the kernel.
@@ -422,10 +454,9 @@ static void do_signal(struct pt_regs *regs)
 			regs->ax = regs->orig_ax;
 			regs->ip -= 2;
 			break;
+
 		case -ERESTART_RESTARTBLOCK:
-			regs->ax = test_thread_flag(TIF_IA32) ?
-					__NR_ia32_restart_syscall :
-					__NR_restart_syscall;
+			regs->ax = NR_restart_syscall;
 			regs->ip -= 2;
 			break;
 		}
@@ -441,14 +472,18 @@ static void do_signal(struct pt_regs *regs)
 	}
 }
 
-void do_notify_resume(struct pt_regs *regs, void *unused,
-		      __u32 thread_info_flags)
+/*
+ * notification of userspace execution resumption
+ * - triggered by the TIF_WORK_MASK flags
+ */
+void
+do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 {
-#ifdef CONFIG_X86_MCE
+#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
 	/* notify userspace of pending MCEs */
 	if (thread_info_flags & _TIF_MCE_NOTIFY)
 		mce_notify_user();
-#endif /* CONFIG_X86_MCE */
+#endif /* CONFIG_X86_64 && CONFIG_X86_MCE */
 
 	/* deal with pending signal delivery */
 	if (thread_info_flags & _TIF_SIGPENDING)
@@ -458,17 +493,23 @@ void do_notify_resume(struct pt_regs *regs, void *unused,
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 	}
+
+#ifdef CONFIG_X86_32
+	clear_thread_flag(TIF_IRET);
+#endif /* CONFIG_X86_32 */
 }
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
 {
 	struct task_struct *me = current;
+
 	if (show_unhandled_signals && printk_ratelimit()) {
-		printk("%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx",
-	       me->comm, me->pid, where, frame, regs->ip,
-		   regs->sp, regs->orig_ax);
+		printk(KERN_INFO
+		       "%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx",
+		       me->comm, me->pid, where, frame,
+		       regs->ip, regs->sp, regs->orig_ax);
 		print_vma_addr(" in ", regs->ip);
-		printk("\n");
+		printk(KERN_CONT "\n");
 	}
 
 	force_sig(SIGSEGV, me);

arch/x86/kernel/smp.c

@@ -214,12 +214,16 @@ void smp_call_function_single_interrupt(struct pt_regs *regs)
 struct smp_ops smp_ops = {
 	.smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
 	.smp_prepare_cpus = native_smp_prepare_cpus,
-	.cpu_up = native_cpu_up,
 	.smp_cpus_done = native_smp_cpus_done,
 
 	.smp_send_stop = native_smp_send_stop,
 	.smp_send_reschedule = native_smp_send_reschedule,
 
+	.cpu_up = native_cpu_up,
+	.cpu_die = native_cpu_die,
+	.cpu_disable = native_cpu_disable,
+	.play_dead = native_play_dead,
+
 	.send_call_func_ipi = native_send_call_func_ipi,
 	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };

arch/x86/kernel/smpboot.c

@@ -52,6 +52,7 @@
 #include <asm/desc.h>
 #include <asm/nmi.h>
 #include <asm/irq.h>
+#include <asm/idle.h>
 #include <asm/smp.h>
 #include <asm/trampoline.h>
 #include <asm/cpu.h>
@@ -1344,25 +1345,9 @@ static void __ref remove_cpu_from_maps(int cpu)
 	numa_remove_cpu(cpu);
 }
 
-int __cpu_disable(void)
+void cpu_disable_common(void)
 {
 	int cpu = smp_processor_id();
-
-	/*
-	 * Perhaps use cpufreq to drop frequency, but that could go
-	 * into generic code.
-	 *
-	 * We won't take down the boot processor on i386 due to some
-	 * interrupts only being able to be serviced by the BSP.
-	 * Especially so if we're not using an IOAPIC	-zwane
-	 */
-	if (cpu == 0)
-		return -EBUSY;
-
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-		stop_apic_nmi_watchdog(NULL);
-	clear_local_APIC();
-
 	/*
 	 * HACK:
 	 * Allow any queued timer interrupts to get serviced
@@ -1380,10 +1365,32 @@ int __cpu_disable(void)
 	remove_cpu_from_maps(cpu);
 	unlock_vector_lock();
 	fixup_irqs(cpu_online_map);
+}
+
+int native_cpu_disable(void)
+{
+	int cpu = smp_processor_id();
+
+	/*
+	 * Perhaps use cpufreq to drop frequency, but that could go
+	 * into generic code.
+	 *
+	 * We won't take down the boot processor on i386 due to some
+	 * interrupts only being able to be serviced by the BSP.
+	 * Especially so if we're not using an IOAPIC	-zwane
+	 */
+	if (cpu == 0)
+		return -EBUSY;
+
+	if (nmi_watchdog == NMI_LOCAL_APIC)
+		stop_apic_nmi_watchdog(NULL);
+	clear_local_APIC();
+
+	cpu_disable_common();
 	return 0;
 }
 
-void __cpu_die(unsigned int cpu)
+void native_cpu_die(unsigned int cpu)
 {
 	/* We don't do anything here: idle task is faking death itself. */
 	unsigned int i;
@@ -1400,15 +1407,45 @@ void __cpu_die(unsigned int cpu)
 	}
 	printk(KERN_ERR "CPU %u didn't die...\n", cpu);
 }
+
+void play_dead_common(void)
+{
+	idle_task_exit();
+	reset_lazy_tlbstate();
+	irq_ctx_exit(raw_smp_processor_id());
+	c1e_remove_cpu(raw_smp_processor_id());
+
+	mb();
+	/* Ack it */
+	__get_cpu_var(cpu_state) = CPU_DEAD;
+
+	/*
+	 * With physical CPU hotplug, we should halt the cpu
+	 */
+	local_irq_disable();
+}
+
+void native_play_dead(void)
+{
+	play_dead_common();
+	wbinvd_halt();
+}
+
 #else /* ... !CONFIG_HOTPLUG_CPU */
-int __cpu_disable(void)
+int native_cpu_disable(void)
 {
 	return -ENOSYS;
 }
 
-void __cpu_die(unsigned int cpu)
+void native_cpu_die(unsigned int cpu)
 {
 	/* We said "no" in __cpu_disable */
 	BUG();
 }
+
+void native_play_dead(void)
+{
+	BUG();
+}
+
 #endif

arch/x86/kernel/tlb_32.c

@@ -241,3 +241,11 @@ void flush_tlb_all(void)
 	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
 
+void reset_lazy_tlbstate(void)
+{
+	int cpu = raw_smp_processor_id();
+
+	per_cpu(cpu_tlbstate, cpu).state = 0;
+	per_cpu(cpu_tlbstate, cpu).active_mm = &init_mm;
+}
+

arch/x86/kernel/traps_32.c

@@ -891,6 +891,7 @@ void __kprobes do_debug(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk = current;
 	unsigned int condition;
+	int si_code;
 
 	trace_hardirqs_fixup();
 
@@ -935,8 +936,9 @@ void __kprobes do_debug(struct pt_regs *regs, long error_code)
 			goto clear_TF_reenable;
 	}
 
+	si_code = get_si_code((unsigned long)condition);
 	/* Ok, finally something we can handle */
-	send_sigtrap(tsk, regs, error_code);
+	send_sigtrap(tsk, regs, error_code, si_code);
 
 	/*
 	 * Disable additional traps. They'll be re-enabled when

arch/x86/kernel/traps_64.c

@@ -940,7 +940,7 @@ asmlinkage void __kprobes do_debug(struct pt_regs *regs,
 	tsk->thread.error_code = error_code;
 	info.si_signo = SIGTRAP;
 	info.si_errno = 0;
-	info.si_code = TRAP_BRKPT;
+	info.si_code = get_si_code(condition);
 	info.si_addr = user_mode(regs) ? (void __user *)regs->ip : NULL;
 	force_sig_info(SIGTRAP, &info, tsk);
 

arch/x86/kernel/xsave.c

@@ -95,7 +95,9 @@ int save_i387_xstate(void __user *buf)
 	 	 * Start with clearing the user buffer. This will present a
 	 	 * clean context for the bytes not touched by the fxsave/xsave.
 		 */
-		__clear_user(buf, sig_xstate_size);
+		err = __clear_user(buf, sig_xstate_size);
+		if (err)
+			return err;
 
 		if (task_thread_info(tsk)->status & TS_XSAVE)
 			err = xsave_user(buf);
@@ -114,6 +116,8 @@ int save_i387_xstate(void __user *buf)
 
 	if (task_thread_info(tsk)->status & TS_XSAVE) {
 		struct _fpstate __user *fx = buf;
+		struct _xstate __user *x = buf;
+		u64 xstate_bv;
 
 		err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved,
 				     sizeof(struct _fpx_sw_bytes));
@@ -121,6 +125,31 @@ int save_i387_xstate(void __user *buf)
 		err |= __put_user(FP_XSTATE_MAGIC2,
 				  (__u32 __user *) (buf + sig_xstate_size
 						    - FP_XSTATE_MAGIC2_SIZE));
+
+		/*
+		 * Read the xstate_bv which we copied (directly from the cpu or
+		 * from the state in task struct) to the user buffers and
+		 * set the FP/SSE bits.
+		 */
+		err |= __get_user(xstate_bv, &x->xstate_hdr.xstate_bv);
+
+		/*
+		 * For legacy compatible, we always set FP/SSE bits in the bit
+		 * vector while saving the state to the user context. This will
+		 * enable us capturing any changes(during sigreturn) to
+		 * the FP/SSE bits by the legacy applications which don't touch
+		 * xstate_bv in the xsave header.
+		 *
+		 * xsave aware apps can change the xstate_bv in the xsave
+		 * header as well as change any contents in the memory layout.
+		 * xrestore as part of sigreturn will capture all the changes.
+		 */
+		xstate_bv |= XSTATE_FPSSE;
+
+		err |= __put_user(xstate_bv, &x->xstate_hdr.xstate_bv);
+
+		if (err)
+			return err;
 	}
 
 	return 1;
@@ -272,7 +301,7 @@ void __cpuinit xsave_init(void)
 /*
  * setup the xstate image representing the init state
  */
-void setup_xstate_init(void)
+static void __init setup_xstate_init(void)
 {
 	init_xstate_buf = alloc_bootmem(xstate_size);
 	init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT;

arch/x86/mm/fault.c

@@ -914,15 +914,15 @@ LIST_HEAD(pgd_list);
 
 void vmalloc_sync_all(void)
 {
-#ifdef CONFIG_X86_32
-	unsigned long start = VMALLOC_START & PGDIR_MASK;
 	unsigned long address;
 
+#ifdef CONFIG_X86_32
 	if (SHARED_KERNEL_PMD)
 		return;
 
-	BUILD_BUG_ON(TASK_SIZE & ~PGDIR_MASK);
-	for (address = start; address >= TASK_SIZE; address += PGDIR_SIZE) {
+	for (address = VMALLOC_START & PMD_MASK;
+	     address >= TASK_SIZE && address < FIXADDR_TOP;
+	     address += PMD_SIZE) {
 		unsigned long flags;
 		struct page *page;
 
@@ -935,10 +935,8 @@ void vmalloc_sync_all(void)
 		spin_unlock_irqrestore(&pgd_lock, flags);
 	}
 #else /* CONFIG_X86_64 */
-	unsigned long start = VMALLOC_START & PGDIR_MASK;
-	unsigned long address;
-
-	for (address = start; address <= VMALLOC_END; address += PGDIR_SIZE) {
+	for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
+	     address += PGDIR_SIZE) {
 		const pgd_t *pgd_ref = pgd_offset_k(address);
 		unsigned long flags;
 		struct page *page;

arch/x86/mm/init_32.c

@@ -31,6 +31,7 @@
 #include <linux/cpumask.h>
 
 #include <asm/asm.h>
+#include <asm/bios_ebda.h>
 #include <asm/processor.h>
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -969,6 +970,8 @@ void __init mem_init(void)
 	int codesize, reservedpages, datasize, initsize;
 	int tmp;
 
+	start_periodic_check_for_corruption();
+
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif

arch/x86/mm/init_64.c

@@ -31,6 +31,7 @@
 #include <linux/nmi.h>
 
 #include <asm/processor.h>
+#include <asm/bios_ebda.h>
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -881,6 +882,8 @@ void __init mem_init(void)
 {
 	long codesize, reservedpages, datasize, initsize;
 
+	start_periodic_check_for_corruption();
+
 	pci_iommu_alloc();
 
 	/* clear_bss() already clear the empty_zero_page */

arch/x86/mm/ioremap.c

@@ -24,18 +24,26 @@
 
 #ifdef CONFIG_X86_64
 
-unsigned long __phys_addr(unsigned long x)
+static inline int phys_addr_valid(unsigned long addr)
 {
-	if (x >= __START_KERNEL_map)
-		return x - __START_KERNEL_map + phys_base;
-	return x - PAGE_OFFSET;
+	return addr < (1UL << boot_cpu_data.x86_phys_bits);
 }
-EXPORT_SYMBOL(__phys_addr);
 
-static inline int phys_addr_valid(unsigned long addr)
+unsigned long __phys_addr(unsigned long x)
 {
-	return addr < (1UL << boot_cpu_data.x86_phys_bits);
+	if (x >= __START_KERNEL_map) {
+		x -= __START_KERNEL_map;
+		VIRTUAL_BUG_ON(x >= KERNEL_IMAGE_SIZE);
+		x += phys_base;
+	} else {
+		VIRTUAL_BUG_ON(x < PAGE_OFFSET);
+		x -= PAGE_OFFSET;
+		VIRTUAL_BUG_ON(system_state == SYSTEM_BOOTING ? x > MAXMEM :
+					!phys_addr_valid(x));
+	}
+	return x;
 }
+EXPORT_SYMBOL(__phys_addr);
 
 #else
 
@@ -44,6 +52,17 @@ static inline int phys_addr_valid(unsigned long addr)
 	return 1;
 }
 
+#ifdef CONFIG_DEBUG_VIRTUAL
+unsigned long __phys_addr(unsigned long x)
+{
+	/* VMALLOC_* aren't constants; not available at the boot time */
+	VIRTUAL_BUG_ON(x < PAGE_OFFSET || (system_state != SYSTEM_BOOTING &&
+					is_vmalloc_addr((void *)x)));
+	return x - PAGE_OFFSET;
+}
+EXPORT_SYMBOL(__phys_addr);
+#endif
+
 #endif
 
 int page_is_ram(unsigned long pagenr)

arch/x86/xen/Kconfig

@@ -26,5 +26,13 @@ config XEN_MAX_DOMAIN_MEMORY
 
 config XEN_SAVE_RESTORE
        bool
-       depends on PM
+       depends on XEN && PM
        default y
+
+config XEN_DEBUG_FS
+	bool "Enable Xen debug and tuning parameters in debugfs"
+	depends on XEN && DEBUG_FS
+	default n
+	help
+	  Enable statistics output and various tuning options in debugfs.
+	  Enabling this option may incur a significant performance overhead.

arch/x86/xen/Makefile

-obj-y		:= enlighten.o setup.o multicalls.o mmu.o \
+ifdef CONFIG_FTRACE
+# Do not profile debug and lowlevel utilities
+CFLAGS_REMOVE_spinlock.o = -pg
+CFLAGS_REMOVE_time.o = -pg
+CFLAGS_REMOVE_irq.o = -pg
+endif
+
+obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 			time.o xen-asm_$(BITS).o grant-table.o suspend.o
 
-obj-$(CONFIG_SMP)	+= smp.o
+obj-$(CONFIG_SMP)		+= smp.o spinlock.o
+obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
\ No newline at end of file

arch/x86/xen/debugfs.c

+#include <linux/init.h>
+#include <linux/debugfs.h>
+#include <linux/module.h>
+
+#include "debugfs.h"
+
+static struct dentry *d_xen_debug;
+
+struct dentry * __init xen_init_debugfs(void)
+{
+	if (!d_xen_debug) {
+		d_xen_debug = debugfs_create_dir("xen", NULL);
+
+		if (!d_xen_debug)
+			pr_warning("Could not create 'xen' debugfs directory\n");
+	}
+
+	return d_xen_debug;
+}
+
+struct array_data
+{
+	void *array;
+	unsigned elements;
+};
+
+static int u32_array_open(struct inode *inode, struct file *file)
+{
+	file->private_data = NULL;
+	return nonseekable_open(inode, file);
+}
+
+static size_t format_array(char *buf, size_t bufsize, const char *fmt,
+			   u32 *array, unsigned array_size)
+{
+	size_t ret = 0;
+	unsigned i;
+
+	for(i = 0; i < array_size; i++) {
+		size_t len;
+
+		len = snprintf(buf, bufsize, fmt, array[i]);
+		len++;	/* ' ' or '\n' */
+		ret += len;
+
+		if (buf) {
+			buf += len;
+			bufsize -= len;
+			buf[-1] = (i == array_size-1) ? '\n' : ' ';
+		}
+	}
+
+	ret++;		/* \0 */
+	if (buf)
+		*buf = '\0';
+
+	return ret;
+}
+
+static char *format_array_alloc(const char *fmt, u32 *array, unsigned array_size)
+{
+	size_t len = format_array(NULL, 0, fmt, array, array_size);
+	char *ret;
+
+	ret = kmalloc(len, GFP_KERNEL);
+	if (ret == NULL)
+		return NULL;
+
+	format_array(ret, len, fmt, array, array_size);
+	return ret;
+}
+
+static ssize_t u32_array_read(struct file *file, char __user *buf, size_t len,
+			      loff_t *ppos)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct array_data *data = inode->i_private;
+	size_t size;
+
+	if (*ppos == 0) {
+		if (file->private_data) {
+			kfree(file->private_data);
+			file->private_data = NULL;
+		}
+
+		file->private_data = format_array_alloc("%u", data->array, data->elements);
+	}
+
+	size = 0;
+	if (file->private_data)
+		size = strlen(file->private_data);
+
+	return simple_read_from_buffer(buf, len, ppos, file->private_data, size);
+}
+
+static int xen_array_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+
+	return 0;
+}
+
+static struct file_operations u32_array_fops = {
+	.owner	= THIS_MODULE,
+	.open	= u32_array_open,
+	.release= xen_array_release,
+	.read	= u32_array_read,
+};
+
+struct dentry *xen_debugfs_create_u32_array(const char *name, mode_t mode,
+					    struct dentry *parent,
+					    u32 *array, unsigned elements)
+{
+	struct array_data *data = kmalloc(sizeof(*data), GFP_KERNEL);
+
+	if (data == NULL)
+		return NULL;
+
+	data->array = array;
+	data->elements = elements;
+
+	return debugfs_create_file(name, mode, parent, data, &u32_array_fops);
+}

arch/x86/xen/debugfs.h

+#ifndef _XEN_DEBUGFS_H
+#define _XEN_DEBUGFS_H
+
+struct dentry * __init xen_init_debugfs(void);
+
+struct dentry *xen_debugfs_create_u32_array(const char *name, mode_t mode,
+					    struct dentry *parent,
+					    u32 *array, unsigned elements);
+
+#endif /* _XEN_DEBUGFS_H */

arch/x86/xen/irq.c

+#include <linux/hardirq.h>
+
+#include <xen/interface/xen.h>
+#include <xen/interface/sched.h>
+#include <xen/interface/vcpu.h>
+
+#include <asm/xen/hypercall.h>
+#include <asm/xen/hypervisor.h>
+
+#include "xen-ops.h"
+
+/*
+ * Force a proper event-channel callback from Xen after clearing the
+ * callback mask. We do this in a very simple manner, by making a call
+ * down into Xen. The pending flag will be checked by Xen on return.
+ */
+void xen_force_evtchn_callback(void)
+{
+	(void)HYPERVISOR_xen_version(0, NULL);
+}
+
+static void __init __xen_init_IRQ(void)
+{
+#ifdef CONFIG_X86_64
+	int i;
+
+	/* Create identity vector->irq map */
+	for(i = 0; i < NR_VECTORS; i++) {
+		int cpu;
+
+		for_each_possible_cpu(cpu)
+			per_cpu(vector_irq, cpu)[i] = i;
+	}
+#endif	/* CONFIG_X86_64 */
+
+	xen_init_IRQ();
+}
+
+static unsigned long xen_save_fl(void)
+{
+	struct vcpu_info *vcpu;
+	unsigned long flags;
+
+	vcpu = x86_read_percpu(xen_vcpu);
+
+	/* flag has opposite sense of mask */
+	flags = !vcpu->evtchn_upcall_mask;
+
+	/* convert to IF type flag
+	   -0 -> 0x00000000
+	   -1 -> 0xffffffff
+	*/
+	return (-flags) & X86_EFLAGS_IF;
+}
+
+static void xen_restore_fl(unsigned long flags)
+{
+	struct vcpu_info *vcpu;
+
+	/* convert from IF type flag */
+	flags = !(flags & X86_EFLAGS_IF);
+
+	/* There's a one instruction preempt window here.  We need to
+	   make sure we're don't switch CPUs between getting the vcpu
+	   pointer and updating the mask. */
+	preempt_disable();
+	vcpu = x86_read_percpu(xen_vcpu);
+	vcpu->evtchn_upcall_mask = flags;
+	preempt_enable_no_resched();
+
+	/* Doesn't matter if we get preempted here, because any
+	   pending event will get dealt with anyway. */
+
+	if (flags == 0) {
+		preempt_check_resched();
+		barrier(); /* unmask then check (avoid races) */
+		if (unlikely(vcpu->evtchn_upcall_pending))
+			xen_force_evtchn_callback();
+	}
+}
+
+static void xen_irq_disable(void)
+{
+	/* There's a one instruction preempt window here.  We need to
+	   make sure we're don't switch CPUs between getting the vcpu
+	   pointer and updating the mask. */
+	preempt_disable();
+	x86_read_percpu(xen_vcpu)->evtchn_upcall_mask = 1;
+	preempt_enable_no_resched();
+}
+
+static void xen_irq_enable(void)
+{
+	struct vcpu_info *vcpu;
+
+	/* We don't need to worry about being preempted here, since
+	   either a) interrupts are disabled, so no preemption, or b)
+	   the caller is confused and is trying to re-enable interrupts
+	   on an indeterminate processor. */
+
+	vcpu = x86_read_percpu(xen_vcpu);
+	vcpu->evtchn_upcall_mask = 0;
+
+	/* Doesn't matter if we get preempted here, because any
+	   pending event will get dealt with anyway. */
+
+	barrier(); /* unmask then check (avoid races) */
+	if (unlikely(vcpu->evtchn_upcall_pending))
+		xen_force_evtchn_callback();
+}
+
+static void xen_safe_halt(void)
+{
+	/* Blocking includes an implicit local_irq_enable(). */
+	if (HYPERVISOR_sched_op(SCHEDOP_block, NULL) != 0)
+		BUG();
+}
+
+static void xen_halt(void)
+{
+	if (irqs_disabled())
+		HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
+	else
+		xen_safe_halt();
+}
+
+static const struct pv_irq_ops xen_irq_ops __initdata = {
+	.init_IRQ = __xen_init_IRQ,
+	.save_fl = xen_save_fl,
+	.restore_fl = xen_restore_fl,
+	.irq_disable = xen_irq_disable,
+	.irq_enable = xen_irq_enable,
+	.safe_halt = xen_safe_halt,
+	.halt = xen_halt,
+#ifdef CONFIG_X86_64
+	.adjust_exception_frame = xen_adjust_exception_frame,
+#endif
+};
+
+void __init xen_init_irq_ops()
+{
+	pv_irq_ops = xen_irq_ops;
+}

arch/x86/xen/mmu.h

@@ -18,9 +18,6 @@ void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next);
 void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm);
 void xen_exit_mmap(struct mm_struct *mm);
 
-void xen_pgd_pin(pgd_t *pgd);
-//void xen_pgd_unpin(pgd_t *pgd);
-
 pteval_t xen_pte_val(pte_t);
 pmdval_t xen_pmd_val(pmd_t);
 pgdval_t xen_pgd_val(pgd_t);

arch/x86/xen/xen-asm_32.S

@@ -298,7 +298,7 @@ check_events:
 	push %eax
 	push %ecx
 	push %edx
-	call force_evtchn_callback
+	call xen_force_evtchn_callback
 	pop %edx
 	pop %ecx
 	pop %eax

drivers/block/xen-blkfront.c

@@ -1066,7 +1066,7 @@ static struct xenbus_driver blkfront = {
 
 static int __init xlblk_init(void)
 {
-	if (!is_running_on_xen())
+	if (!xen_domain())
 		return -ENODEV;
 
 	if (register_blkdev(XENVBD_MAJOR, DEV_NAME)) {