Merge branches 'x86/apic', 'x86/cleanups', 'x86/cpufeature', 'x86/crashdump', 'x86/debug', 'x86/defconfig', 'x86/detect-hyper', 'x86/doc', 'x86/dumpstack', 'x86/early-printk', 'x86/fpu', 'x86/idle', 'x86/io', 'x86/memory-corruption-check', 'x86/microcode', 'x86/mm', 'x86/mtrr', 'x86/nmi-watchdog', 'x86/pat2', 'x86/pci-ioapic-boot-irq-quirks', 'x86/ptrace', 'x86/quirks', 'x86/reboot', 'x86/setup-memory', 'x86/signal', 'x86/sparse-fixes', 'x86/time', 'x86/uv' and 'x86/xen' into x86/core

Documentation/feature-removal-schedule.txt

@@ -244,18 +244,6 @@ Who:	Michael Buesch <mb@bu3sch.de>
 
 ---------------------------
 
-What:	init_mm export
-When:	2.6.26
-Why:	Not used in-tree. The current out-of-tree users used it to
-	work around problems in the CPA code which should be resolved
-	by now. One usecase was described to provide verification code
-	of the CPA operation. That's a good idea in general, but such
-	code / infrastructure should be in the kernel and not in some
-	out-of-tree driver.
-Who:	Thomas Gleixner <tglx@linutronix.de>
-
-----------------------------
-
 What:	usedac i386 kernel parameter
 When:	2.6.27
 Why:	replaced by allowdac and no dac combination

Documentation/filesystems/proc.txt

@@ -1339,10 +1339,13 @@ nmi_watchdog
 
 Enables/Disables the NMI watchdog on x86 systems.  When the value is non-zero
 the NMI watchdog is enabled and will continuously test all online cpus to
-determine whether or not they are still functioning properly.
+determine whether or not they are still functioning properly. Currently,
+passing "nmi_watchdog=" parameter at boot time is required for this function
+to work.
 
-Because the NMI watchdog shares registers with oprofile, by disabling the NMI
-watchdog, oprofile may have more registers to utilize.
+If LAPIC NMI watchdog method is in use (nmi_watchdog=2 kernel parameter), the
+NMI watchdog shares registers with oprofile. By disabling the NMI watchdog,
+oprofile may have more registers to utilize.
 
 msgmni
 ------

Documentation/kernel-parameters.txt

@@ -1393,7 +1393,20 @@ and is between 256 and 4096 characters. It is defined in the file
 			when a NMI is triggered.
 			Format: [state][,regs][,debounce][,die]
 
-	nmi_watchdog=	[KNL,BUGS=X86-32] Debugging features for SMP kernels
+	nmi_watchdog=	[KNL,BUGS=X86-32,X86-64] Debugging features for SMP kernels
+			Format: [panic,][num]
+			Valid num: 0,1,2
+			0 - turn nmi_watchdog off
+			1 - use the IO-APIC timer for the NMI watchdog
+			2 - use the local APIC for the NMI watchdog using
+			a performance counter. Note: This will use one performance
+			counter and the local APIC's performance vector.
+			When panic is specified panic when an NMI watchdog timeout occurs.
+			This is useful when you use a panic=... timeout and need the box
+			quickly up again.
+			Instead of 1 and 2 it is possible to use the following
+			symbolic names: lapic and ioapic
+			Example: nmi_watchdog=2 or nmi_watchdog=panic,lapic
 
 	no387		[BUGS=X86-32] Tells the kernel to use the 387 maths
 			emulation library even if a 387 maths coprocessor
@@ -1626,6 +1639,17 @@ and is between 256 and 4096 characters. It is defined in the file
 		nomsi		[MSI] If the PCI_MSI kernel config parameter is
 				enabled, this kernel boot option can be used to
 				disable the use of MSI interrupts system-wide.
+		noioapicquirk	[APIC] Disable all boot interrupt quirks.
+				Safety option to keep boot IRQs enabled. This
+				should never be necessary.
+		ioapicreroute	[APIC] Enable rerouting of boot IRQs to the
+				primary IO-APIC for bridges that cannot disable
+				boot IRQs. This fixes a source of spurious IRQs
+				when the system masks IRQs.
+		noioapicreroute	[APIC] Disable workaround that uses the
+				boot IRQ equivalent of an IRQ that connects to
+				a chipset where boot IRQs cannot be disabled.
+				The opposite of ioapicreroute.
 		biosirq		[X86-32] Use PCI BIOS calls to get the interrupt
 				routing table. These calls are known to be buggy
 				on several machines and they hang the machine
@@ -2255,6 +2279,13 @@ and is between 256 and 4096 characters. It is defined in the file
 			Format:
 			<io>,<irq>,<dma>,<dma2>,<sb_io>,<sb_irq>,<sb_dma>,<mpu_io>,<mpu_irq>
 
+	tsc=		Disable clocksource-must-verify flag for TSC.
+			Format: <string>
+			[x86] reliable: mark tsc clocksource as reliable, this
+			disables clocksource verification at runtime.
+			Used to enable high-resolution timer mode on older
+			hardware, and in virtualized environment.
+
 	turbografx.map[2|3]=	[HW,JOY]
 			TurboGraFX parallel port interface
 			Format:

Documentation/nmi_watchdog.txt

@@ -69,6 +69,11 @@ to the overall system performance.
 On x86 nmi_watchdog is disabled by default so you have to enable it with
 a boot time parameter.
 
+It's possible to disable the NMI watchdog in run-time by writing "0" to
+/proc/sys/kernel/nmi_watchdog. Writing "1" to the same file will re-enable
+the NMI watchdog. Notice that you still need to use "nmi_watchdog=" parameter
+at boot time.
+
 NOTE: In kernels prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
 on x86 SMP boxes.
 

Documentation/x86/boot.txt

@@ -349,7 +349,7 @@ Protocol:	2.00+
 	3  SYSLINUX
 	4  EtherBoot
 	5  ELILO
-	7  GRuB
+	7  GRUB
 	8  U-BOOT
 	9  Xen
 	A  Gujin
@@ -537,8 +537,8 @@ Type:		read
 Offset/size:	0x248/4
 Protocol:	2.08+
 
-  If non-zero then this field contains the offset from the end of the
-  real-mode code to the payload.
+  If non-zero then this field contains the offset from the beginning
+  of the protected-mode code to the payload.
 
   The payload may be compressed. The format of both the compressed and
   uncompressed data should be determined using the standard magic

Documentation/x86/pat.txt

@@ -80,6 +80,30 @@ pci proc               |    --    |    --      |       WC         |
                        |          |            |                  |
 -------------------------------------------------------------------
 
+Advanced APIs for drivers
+-------------------------
+A. Exporting pages to users with remap_pfn_range, io_remap_pfn_range,
+vm_insert_pfn
+
+Drivers wanting to export some pages to userspace do it by using mmap
+interface and a combination of
+1) pgprot_noncached()
+2) io_remap_pfn_range() or remap_pfn_range() or vm_insert_pfn()
+
+With PAT support, a new API pgprot_writecombine is being added. So, drivers can
+continue to use the above sequence, with either pgprot_noncached() or
+pgprot_writecombine() in step 1, followed by step 2.
+
+In addition, step 2 internally tracks the region as UC or WC in memtype
+list in order to ensure no conflicting mapping.
+
+Note that this set of APIs only works with IO (non RAM) regions. If driver
+wants to export a RAM region, it has to do set_memory_uc() or set_memory_wc()
+as step 0 above and also track the usage of those pages and use set_memory_wb()
+before the page is freed to free pool.
+
+
+
 Notes:
 
 -- in the above table mean "Not suggested usage for the API". Some of the --'s

Documentation/x86/x86_64/boot-options.txt

@@ -79,17 +79,6 @@ Timing
   Report when timer interrupts are lost because some code turned off
   interrupts for too long.
 
-  nmi_watchdog=NUMBER[,panic]
-  NUMBER can be:
-  0 don't use an NMI watchdog
-  1 use the IO-APIC timer for the NMI watchdog
-  2 use the local APIC for the NMI watchdog using a performance counter. Note
-  This will use one performance counter and the local APIC's performance
-  vector.
-  When panic is specified panic when an NMI watchdog timeout occurs.
-  This is useful when you use a panic=... timeout and need the box
-  quickly up again.
-
   nohpet
   Don't use the HPET timer.
 

Documentation/x86/x86_64/mm.txt

@@ -6,7 +6,7 @@ Virtual memory map with 4 level page tables:
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
 hole caused by [48:63] sign extension
 ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
-ffff810000000000 - ffffc0ffffffffff (=46 bits) direct mapping of all phys. memory
+ffff880000000000 - ffffc0ffffffffff (=57 TB) direct mapping of all phys. memory
 ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
 ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
 ffffe20000000000 - ffffe2ffffffffff (=40 bits) virtual memory map (1TB)

arch/x86/Kconfig

@@ -19,6 +19,8 @@ config X86_64
 config X86
 	def_bool y
 	select HAVE_AOUT if X86_32
+	select HAVE_READQ
+	select HAVE_WRITEQ
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_IDE
 	select HAVE_OPROFILE
@@ -87,6 +89,10 @@ config GENERIC_IOMAP
 config GENERIC_BUG
 	def_bool y
 	depends on BUG
+	select GENERIC_BUG_RELATIVE_POINTERS if X86_64
+
+config GENERIC_BUG_RELATIVE_POINTERS
+	bool
 
 config GENERIC_HWEIGHT
 	def_bool y
@@ -242,21 +248,13 @@ config X86_FIND_SMP_CONFIG
 	def_bool y
 	depends on X86_MPPARSE || X86_VOYAGER
 
-if ACPI
 config X86_MPPARSE
-	def_bool y
-	bool "Enable MPS table"
+	bool "Enable MPS table" if ACPI
+	default y
 	depends on X86_LOCAL_APIC
 	help
 	  For old smp systems that do not have proper acpi support. Newer systems
 	  (esp with 64bit cpus) with acpi support, MADT and DSDT will override it
-endif
-
-if !ACPI
-config X86_MPPARSE
-	def_bool y
-	depends on X86_LOCAL_APIC
-endif
 
 choice
 	prompt "Subarchitecture Type"
@@ -465,10 +463,6 @@ config X86_CYCLONE_TIMER
 	def_bool y
 	depends on X86_GENERICARCH
 
-config ES7000_CLUSTERED_APIC
-	def_bool y
-	depends on SMP && X86_ES7000 && MPENTIUMIII
-
 source "arch/x86/Kconfig.cpu"
 
 config HPET_TIMER
@@ -660,6 +654,30 @@ config X86_VISWS_APIC
 	def_bool y
 	depends on X86_32 && X86_VISWS
 
+config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
+	bool "Reroute for broken boot IRQs"
+	default n
+	depends on X86_IO_APIC
+	help
+	  This option enables a workaround that fixes a source of
+	  spurious interrupts. This is recommended when threaded
+	  interrupt handling is used on systems where the generation of
+	  superfluous "boot interrupts" cannot be disabled.
+
+	  Some chipsets generate a legacy INTx "boot IRQ" when the IRQ
+	  entry in the chipset's IO-APIC is masked (as, e.g. the RT
+	  kernel does during interrupt handling). On chipsets where this
+	  boot IRQ generation cannot be disabled, this workaround keeps
+	  the original IRQ line masked so that only the equivalent "boot
+	  IRQ" is delivered to the CPUs. The workaround also tells the
+	  kernel to set up the IRQ handler on the boot IRQ line. In this
+	  way only one interrupt is delivered to the kernel. Otherwise
+	  the spurious second interrupt may cause the kernel to bring
+	  down (vital) interrupt lines.
+
+	  Only affects "broken" chipsets. Interrupt sharing may be
+	  increased on these systems.
+
 config X86_MCE
 	bool "Machine Check Exception"
 	depends on !X86_VOYAGER
@@ -956,24 +974,37 @@ config X86_PAE
 config ARCH_PHYS_ADDR_T_64BIT
        def_bool X86_64 || X86_PAE
 
+config DIRECT_GBPAGES
+	bool "Enable 1GB pages for kernel pagetables" if EMBEDDED
+	default y
+	depends on X86_64
+	help
+	  Allow the kernel linear mapping to use 1GB pages on CPUs that
+	  support it. This can improve the kernel's performance a tiny bit by
+	  reducing TLB pressure. If in doubt, say "Y".
+
 # Common NUMA Features
 config NUMA
-	bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
+	bool "Numa Memory Allocation and Scheduler Support"
 	depends on SMP
 	depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL)
 	default n if X86_PC
 	default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP)
 	help
 	  Enable NUMA (Non Uniform Memory Access) support.
+
 	  The kernel will try to allocate memory used by a CPU on the
 	  local memory controller of the CPU and add some more
 	  NUMA awareness to the kernel.
 
-	  For 32-bit this is currently highly experimental and should be only
-	  used for kernel development. It might also cause boot failures.
-	  For 64-bit this is recommended on all multiprocessor Opteron systems.
-	  If the system is EM64T, you should say N unless your system is
-	  EM64T NUMA.
+	  For 64-bit this is recommended if the system is Intel Core i7
+	  (or later), AMD Opteron, or EM64T NUMA.
+
+	  For 32-bit this is only needed on (rare) 32-bit-only platforms
+	  that support NUMA topologies, such as NUMAQ / Summit, or if you
+	  boot a 32-bit kernel on a 64-bit NUMA platform.
+
+	  Otherwise, you should say N.
 
 comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
 	depends on X86_32 && X86_SUMMIT && (!HIGHMEM64G || !ACPI)
@@ -1493,6 +1524,10 @@ config ARCH_ENABLE_MEMORY_HOTPLUG
 	def_bool y
 	depends on X86_64 || (X86_32 && HIGHMEM)
 
+config ARCH_ENABLE_MEMORY_HOTREMOVE
+	def_bool y
+	depends on MEMORY_HOTPLUG
+
 config HAVE_ARCH_EARLY_PFN_TO_NID
 	def_bool X86_64
 	depends on NUMA
@@ -1632,13 +1667,6 @@ config APM_ALLOW_INTS
 	  many of the newer IBM Thinkpads.  If you experience hangs when you
 	  suspend, try setting this to Y.  Otherwise, say N.
 
-config APM_REAL_MODE_POWER_OFF
-	bool "Use real mode APM BIOS call to power off"
-	help
-	  Use real mode APM BIOS calls to switch off the computer. This is
-	  a work-around for a number of buggy BIOSes. Switch this option on if
-	  your computer crashes instead of powering off properly.
-
 endif # APM
 
 source "arch/x86/kernel/cpu/cpufreq/Kconfig"

arch/x86/Kconfig.debug

@@ -114,18 +114,6 @@ config DEBUG_RODATA
 	  data. This is recommended so that we can catch kernel bugs sooner.
 	  If in doubt, say "Y".
 
-config DIRECT_GBPAGES
-	bool "Enable gbpages-mapped kernel pagetables"
-	depends on DEBUG_KERNEL && EXPERIMENTAL && X86_64
-	help
-	  Enable gigabyte pages support (if the CPU supports it). This can
-	  improve the kernel's performance a tiny bit by reducing TLB
-	  pressure.
-
-	  This is experimental code.
-
-	  If in doubt, say "N".
-
 config DEBUG_RODATA_TEST
 	bool "Testcase for the DEBUG_RODATA feature"
 	depends on DEBUG_RODATA
@@ -307,10 +295,10 @@ config OPTIMIZE_INLINING
 	  developers have marked 'inline'. Doing so takes away freedom from gcc to
 	  do what it thinks is best, which is desirable for the gcc 3.x series of
 	  compilers. The gcc 4.x series have a rewritten inlining algorithm and
-	  disabling this option will generate a smaller kernel there. Hopefully
-	  this algorithm is so good that allowing gcc4 to make the decision can
-	  become the default in the future, until then this option is there to
-	  test gcc for this.
+	  enabling this option will generate a smaller kernel there. Hopefully
+	  this algorithm is so good that allowing gcc 4.x and above to make the
+	  decision will become the default in the future. Until then this option
+	  is there to test gcc for this.
 
 	  If unsure, say N.
 

arch/x86/boot/video-vga.c

@@ -34,7 +34,7 @@ static struct mode_info cga_modes[] = {
 	{ VIDEO_80x25,  80, 25, 0 },
 };
 
-__videocard video_vga;
+static __videocard video_vga;
 
 /* Set basic 80x25 mode */
 static u8 vga_set_basic_mode(void)
@@ -259,7 +259,7 @@ static int vga_probe(void)
 	return mode_count[adapter];
 }
 
-__videocard video_vga = {
+static __videocard video_vga = {
 	.card_name	= "VGA",
 	.probe		= vga_probe,
 	.set_mode	= vga_set_mode,

arch/x86/boot/video.c

@@ -226,7 +226,7 @@ static unsigned int mode_menu(void)
 
 #ifdef CONFIG_VIDEO_RETAIN
 /* Save screen content to the heap */
-struct saved_screen {
+static struct saved_screen {
 	int x, y;
 	int curx, cury;
 	u16 *data;

arch/x86/configs/i386_defconfig

@@ -77,7 +77,7 @@ CONFIG_AUDIT=y
 CONFIG_AUDITSYSCALL=y
 CONFIG_AUDIT_TREE=y
 # CONFIG_IKCONFIG is not set
-CONFIG_LOG_BUF_SHIFT=17
+CONFIG_LOG_BUF_SHIFT=18
 CONFIG_CGROUPS=y
 # CONFIG_CGROUP_DEBUG is not set
 CONFIG_CGROUP_NS=y
@@ -298,7 +298,7 @@ CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
 # CONFIG_KEXEC_JUMP is not set
 CONFIG_PHYSICAL_START=0x1000000
-CONFIG_RELOCATABLE=y
+# CONFIG_RELOCATABLE is not set
 CONFIG_PHYSICAL_ALIGN=0x200000
 CONFIG_HOTPLUG_CPU=y
 # CONFIG_COMPAT_VDSO is not set

arch/x86/configs/x86_64_defconfig

@@ -77,7 +77,7 @@ CONFIG_AUDIT=y
 CONFIG_AUDITSYSCALL=y
 CONFIG_AUDIT_TREE=y
 # CONFIG_IKCONFIG is not set
-CONFIG_LOG_BUF_SHIFT=17
+CONFIG_LOG_BUF_SHIFT=18
 CONFIG_CGROUPS=y
 # CONFIG_CGROUP_DEBUG is not set
 CONFIG_CGROUP_NS=y
@@ -298,7 +298,7 @@ CONFIG_SCHED_HRTICK=y
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
 CONFIG_PHYSICAL_START=0x1000000
-CONFIG_RELOCATABLE=y
+# CONFIG_RELOCATABLE is not set
 CONFIG_PHYSICAL_ALIGN=0x200000
 CONFIG_HOTPLUG_CPU=y
 # CONFIG_COMPAT_VDSO is not set

arch/x86/ia32/ia32_signal.c

@@ -32,6 +32,8 @@
 #include <asm/proto.h>
 #include <asm/vdso.h>
 
+#include <asm/sigframe.h>
+
 #define DEBUG_SIG 0
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
@@ -41,7 +43,6 @@
 			 X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
 			 X86_EFLAGS_CF)
 
-asmlinkage int do_signal(struct pt_regs *regs, sigset_t *oldset);
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
 
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
@@ -173,47 +174,28 @@ asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr,
 /*
  * Do a signal return; undo the signal stack.
  */
+#define COPY(x)			{		\
+	err |= __get_user(regs->x, &sc->x);	\
+}
 
-struct sigframe
-{
-	u32 pretcode;
-	int sig;
-	struct sigcontext_ia32 sc;
-	struct _fpstate_ia32 fpstate_unused; /* look at kernel/sigframe.h */
-	unsigned int extramask[_COMPAT_NSIG_WORDS-1];
-	char retcode[8];
-	/* fp state follows here */
-};
-
-struct rt_sigframe
-{
-	u32 pretcode;
-	int sig;
-	u32 pinfo;
-	u32 puc;
-	compat_siginfo_t info;
-	struct ucontext_ia32 uc;
-	char retcode[8];
-	/* fp state follows here */
-};
-
-#define COPY(x)		{ 		\
-	unsigned int reg;		\
-	err |= __get_user(reg, &sc->x);	\
-	regs->x = reg;			\
+#define COPY_SEG_CPL3(seg)	{			\
+		unsigned short tmp;			\
+		err |= __get_user(tmp, &sc->seg);	\
+		regs->seg = tmp | 3;			\
 }
 
-#define RELOAD_SEG(seg,mask)						\
-	{ unsigned int cur;						\
-	  unsigned short pre;						\
-	  err |= __get_user(pre, &sc->seg);				\
-	  savesegment(seg, cur);					\
-	  pre |= mask;							\
-	  if (pre != cur) loadsegment(seg, pre); }
+#define RELOAD_SEG(seg)		{		\
+	unsigned int cur, pre;			\
+	err |= __get_user(pre, &sc->seg);	\
+	savesegment(seg, cur);			\
+	pre |= 3;				\
+	if (pre != cur)				\
+		loadsegment(seg, pre);		\
+}
 
 static int ia32_restore_sigcontext(struct pt_regs *regs,
 				   struct sigcontext_ia32 __user *sc,
-				   unsigned int *peax)
+				   unsigned int *pax)
 {
 	unsigned int tmpflags, gs, oldgs, err = 0;
 	void __user *buf;
@@ -240,18 +222,16 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 	if (gs != oldgs)
 		load_gs_index(gs);
 
-	RELOAD_SEG(fs, 3);
-	RELOAD_SEG(ds, 3);
-	RELOAD_SEG(es, 3);
+	RELOAD_SEG(fs);
+	RELOAD_SEG(ds);
+	RELOAD_SEG(es);
 
 	COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
 	COPY(dx); COPY(cx); COPY(ip);
 	/* Don't touch extended registers */
 
-	err |= __get_user(regs->cs, &sc->cs);
-	regs->cs |= 3;
-	err |= __get_user(regs->ss, &sc->ss);
-	regs->ss |= 3;
+	COPY_SEG_CPL3(cs);
+	COPY_SEG_CPL3(ss);
 
 	err |= __get_user(tmpflags, &sc->flags);
 	regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -262,15 +242,13 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 	buf = compat_ptr(tmp);
 	err |= restore_i387_xstate_ia32(buf);
 
-	err |= __get_user(tmp, &sc->ax);
-	*peax = tmp;
-
+	err |= __get_user(*pax, &sc->ax);
 	return err;
 }
 
 asmlinkage long sys32_sigreturn(struct pt_regs *regs)
 {
-	struct sigframe __user *frame = (struct sigframe __user *)(regs->sp-8);
+	struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8);
 	sigset_t set;
 	unsigned int ax;
 
@@ -300,12 +278,12 @@ badframe:
 
 asmlinkage long sys32_rt_sigreturn(struct pt_regs *regs)
 {
-	struct rt_sigframe __user *frame;
+	struct rt_sigframe_ia32 __user *frame;
 	sigset_t set;
 	unsigned int ax;
 	struct pt_regs tregs;
 
-	frame = (struct rt_sigframe __user *)(regs->sp - 4);
+	frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4);
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
@@ -359,20 +337,15 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
 	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(regs->ip, &sc->ip);
+	err |= __put_user(regs->cs, (unsigned int __user *)&sc->cs);
 	err |= __put_user(regs->flags, &sc->flags);
 	err |= __put_user(regs->sp, &sc->sp_at_signal);
+	err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss);
 
-	tmp = save_i387_xstate_ia32(fpstate);
-	if (tmp < 0)
-		err = -EFAULT;
-	else
-		err |= __put_user(ptr_to_compat(tmp ? fpstate : NULL),
-					&sc->fpstate);
+	err |= __put_user(ptr_to_compat(fpstate), &sc->fpstate);
 
 	/* non-iBCS2 extensions.. */
 	err |= __put_user(mask, &sc->oldmask);
@@ -400,7 +373,7 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
 	}
 
 	/* This is the legacy signal stack switching. */
-	else if ((regs->ss & 0xffff) != __USER_DS &&
+	else if ((regs->ss & 0xffff) != __USER32_DS &&
 		!(ka->sa.sa_flags & SA_RESTORER) &&
 		 ka->sa.sa_restorer)
 		sp = (unsigned long) ka->sa.sa_restorer;
@@ -408,6 +381,8 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
 	if (used_math()) {
 		sp = sp - sig_xstate_ia32_size;
 		*fpstate = (struct _fpstate_ia32 *) sp;
+		if (save_i387_xstate_ia32(*fpstate) < 0)
+			return (void __user *) -1L;
 	}
 
 	sp -= frame_size;
@@ -420,7 +395,7 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
 int ia32_setup_frame(int sig, struct k_sigaction *ka,
 		     compat_sigset_t *set, struct pt_regs *regs)
 {
-	struct sigframe __user *frame;
+	struct sigframe_ia32 __user *frame;
 	void __user *restorer;
 	int err = 0;
 	void __user *fpstate = NULL;
@@ -430,12 +405,10 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 		u16 poplmovl;
 		u32 val;
 		u16 int80;
-		u16 pad;
 	} __attribute__((packed)) code = {
 		0xb858,		 /* popl %eax ; movl $...,%eax */
 		__NR_ia32_sigreturn,
 		0x80cd,		/* int $0x80 */
-		0,
 	};
 
 	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
@@ -471,7 +444,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 	 * These are actually not used anymore, but left because some
 	 * gdb versions depend on them as a marker.
 	 */
-	err |= __copy_to_user(frame->retcode, &code, 8);
+	err |= __put_user(*((u64 *)&code), (u64 *)frame->retcode);
 	if (err)
 		return -EFAULT;
 
@@ -501,7 +474,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 			compat_sigset_t *set, struct pt_regs *regs)
 {
-	struct rt_sigframe __user *frame;
+	struct rt_sigframe_ia32 __user *frame;
 	void __user *restorer;
 	int err = 0;
 	void __user *fpstate = NULL;
@@ -511,8 +484,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		u8 movl;
 		u32 val;
 		u16 int80;
-		u16 pad;
-		u8  pad2;
+		u8  pad;
 	} __attribute__((packed)) code = {
 		0xb8,
 		__NR_ia32_rt_sigreturn,
@@ -559,7 +531,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	 * Not actually used anymore, but left because some gdb
 	 * versions need it.
 	 */
-	err |= __copy_to_user(frame->retcode, &code, 8);
+	err |= __put_user(*((u64 *)&code), (u64 *)frame->retcode);
 	if (err)
 		return -EFAULT;
 
@@ -572,11 +544,6 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	regs->dx = (unsigned long) &frame->info;
 	regs->cx = (unsigned long) &frame->uc;
 
-	/* Make -mregparm=3 work */
-	regs->ax = sig;
-	regs->dx = (unsigned long) &frame->info;
-	regs->cx = (unsigned long) &frame->uc;
-
 	loadsegment(ds, __USER32_DS);
 	loadsegment(es, __USER32_DS);
 

arch/x86/include/asm/apic.h

@@ -193,6 +193,7 @@ extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
 static inline void lapic_shutdown(void) { }
 #define local_apic_timer_c2_ok		1
 static inline void init_apic_mappings(void) { }
+static inline void disable_local_APIC(void) { }
 
 #endif /* !CONFIG_X86_LOCAL_APIC */
 

arch/x86/include/asm/bigsmp/apic.h

@@ -24,8 +24,6 @@ static inline cpumask_t target_cpus(void)
 #define INT_DELIVERY_MODE	(dest_Fixed)
 #define INT_DEST_MODE		(0)    /* phys delivery to target proc */
 #define NO_BALANCE_IRQ		(0)
-#define WAKE_SECONDARY_VIA_INIT
-
 
 static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
 {

arch/x86/include/asm/bitops.h

@@ -168,7 +168,15 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
  */
 static inline void change_bit(int nr, volatile unsigned long *addr)
 {
-	asm volatile(LOCK_PREFIX "btc %1,%0" : ADDR : "Ir" (nr));
+	if (IS_IMMEDIATE(nr)) {
+		asm volatile(LOCK_PREFIX "xorb %1,%0"
+			: CONST_MASK_ADDR(nr, addr)
+			: "iq" ((u8)CONST_MASK(nr)));
+	} else {
+		asm volatile(LOCK_PREFIX "btc %1,%0"
+			: BITOP_ADDR(addr)
+			: "Ir" (nr));
+	}
 }
 
 /**

arch/x86/include/asm/bug.h

@@ -9,7 +9,7 @@
 #ifdef CONFIG_X86_32
 # define __BUG_C0	"2:\t.long 1b, %c0\n"
 #else
-# define __BUG_C0	"2:\t.quad 1b, %c0\n"
+# define __BUG_C0	"2:\t.long 1b - 2b, %c0 - 2b\n"
 #endif
 
 #define BUG()							\

arch/x86/include/asm/byteorder.h

@@ -4,26 +4,33 @@
 #include <asm/types.h>
 #include <linux/compiler.h>
 
-#ifdef __GNUC__
+#define __LITTLE_ENDIAN
 
-#ifdef __i386__
-
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
+static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
 {
-#ifdef CONFIG_X86_BSWAP
-	asm("bswap %0" : "=r" (x) : "0" (x));
-#else
+#ifdef __i386__
+# ifdef CONFIG_X86_BSWAP
+	asm("bswap %0" : "=r" (val) : "0" (val));
+# else
 	asm("xchgb %b0,%h0\n\t"	/* swap lower bytes	*/
 	    "rorl $16,%0\n\t"	/* swap words		*/
 	    "xchgb %b0,%h0"	/* swap higher bytes	*/
-	    : "=q" (x)
-	    : "0" (x));
+	    : "=q" (val)
+	    : "0" (val));
+# endif
+
+#else /* __i386__ */
+	asm("bswapl %0"
+	    : "=r" (val)
+	    : "0" (val));
 #endif
-	return x;
+	return val;
 }
+#define __arch_swab32 __arch_swab32
 
-static inline __attribute_const__ __u64 ___arch__swab64(__u64 val)
+static inline __attribute_const__ __u64 __arch_swab64(__u64 val)
 {
+#ifdef __i386__
 	union {
 		struct {
 			__u32 a;
@@ -32,50 +39,27 @@ static inline __attribute_const__ __u64 ___arch__swab64(__u64 val)
 		__u64 u;
 	} v;
 	v.u = val;
-#ifdef CONFIG_X86_BSWAP
+# ifdef CONFIG_X86_BSWAP
 	asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1"
 	    : "=r" (v.s.a), "=r" (v.s.b)
 	    : "0" (v.s.a), "1" (v.s.b));
-#else
-	v.s.a = ___arch__swab32(v.s.a);
-	v.s.b = ___arch__swab32(v.s.b);
+# else
+	v.s.a = __arch_swab32(v.s.a);
+	v.s.b = __arch_swab32(v.s.b);
 	asm("xchgl %0,%1"
 	    : "=r" (v.s.a), "=r" (v.s.b)
 	    : "0" (v.s.a), "1" (v.s.b));
-#endif
+# endif
 	return v.u;
-}
-
 #else /* __i386__ */
-
-static inline __attribute_const__ __u64 ___arch__swab64(__u64 x)
-{
 	asm("bswapq %0"
-	    : "=r" (x)
-	    : "0" (x));
-	return x;
-}
-
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
-{
-	asm("bswapl %0"
-	    : "=r" (x)
-	    : "0" (x));
-	return x;
-}
-
+	    : "=r" (val)
+	    : "0" (val));
+	return val;
 #endif
+}
+#define __arch_swab64 __arch_swab64
 
-/* Do not define swab16.  Gcc is smart enough to recognize "C" version and
-   convert it into rotation or exhange.  */
-
-#define __arch__swab64(x) ___arch__swab64(x)
-#define __arch__swab32(x) ___arch__swab32(x)
-
-#define __BYTEORDER_HAS_U64__
-
-#endif /* __GNUC__ */
-
-#include <linux/byteorder/little_endian.h>
+#include <linux/byteorder.h>
 
 #endif /* _ASM_X86_BYTEORDER_H */

arch/x86/include/asm/cpufeature.h

@@ -80,7 +80,6 @@
 #define X86_FEATURE_UP		(3*32+ 9) /* smp kernel running on up */
 #define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
 #define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_PEBS	(3*32+12) /* Precise-Event Based Sampling */
 #define X86_FEATURE_BTS		(3*32+13) /* Branch Trace Store */
 #define X86_FEATURE_SYSCALL32	(3*32+14) /* "" syscall in ia32 userspace */
@@ -92,6 +91,8 @@
 #define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_AMDC1E	(3*32+21) /* AMD C1E detected */
 #define X86_FEATURE_XTOPOLOGY	(3*32+22) /* cpu topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
@@ -117,6 +118,7 @@
 #define X86_FEATURE_XSAVE	(4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
 #define X86_FEATURE_OSXSAVE	(4*32+27) /* "" XSAVE enabled in the OS */
 #define X86_FEATURE_AVX		(4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_HYPERVISOR	(4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
 #define X86_FEATURE_XSTORE	(5*32+ 2) /* "rng" RNG present (xstore) */
@@ -237,6 +239,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_xmm4_2		boot_cpu_has(X86_FEATURE_XMM4_2)
 #define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
 #define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
+#define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg		1

arch/x86/include/asm/emergency-restart.h

@@ -8,7 +8,9 @@ enum reboot_type {
 	BOOT_BIOS = 'b',
 #endif
 	BOOT_ACPI = 'a',
-	BOOT_EFI = 'e'
+	BOOT_EFI = 'e',
+	BOOT_CF9 = 'p',
+	BOOT_CF9_COND = 'q',
 };
 
 extern enum reboot_type reboot_type;

arch/x86/include/asm/es7000/apic.h

@@ -9,31 +9,27 @@ static inline int apic_id_registered(void)
 	        return (1);
 }
 
-static inline cpumask_t target_cpus(void)
+static inline cpumask_t target_cpus_cluster(void)
 {
-#if defined CONFIG_ES7000_CLUSTERED_APIC
 	return CPU_MASK_ALL;
-#else
+}
+
+static inline cpumask_t target_cpus(void)
+{
 	return cpumask_of_cpu(smp_processor_id());
-#endif
 }
 
-#if defined CONFIG_ES7000_CLUSTERED_APIC
-#define APIC_DFR_VALUE		(APIC_DFR_CLUSTER)
-#define INT_DELIVERY_MODE	(dest_LowestPrio)
-#define INT_DEST_MODE		(1)    /* logical delivery broadcast to all procs */
-#define NO_BALANCE_IRQ		(1)
-#undef  WAKE_SECONDARY_VIA_INIT
-#define WAKE_SECONDARY_VIA_MIP
-#else
+#define APIC_DFR_VALUE_CLUSTER		(APIC_DFR_CLUSTER)
+#define INT_DELIVERY_MODE_CLUSTER	(dest_LowestPrio)
+#define INT_DEST_MODE_CLUSTER		(1) /* logical delivery broadcast to all procs */
+#define NO_BALANCE_IRQ_CLUSTER		(1)
+
 #define APIC_DFR_VALUE		(APIC_DFR_FLAT)
 #define INT_DELIVERY_MODE	(dest_Fixed)
 #define INT_DEST_MODE		(0)    /* phys delivery to target procs */
 #define NO_BALANCE_IRQ		(0)
 #undef  APIC_DEST_LOGICAL
 #define APIC_DEST_LOGICAL	0x0
-#define WAKE_SECONDARY_VIA_INIT
-#endif
 
 static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
 {
@@ -60,6 +56,16 @@ static inline unsigned long calculate_ldr(int cpu)
  * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
  * document number 292116).  So here it goes...
  */
+static inline void init_apic_ldr_cluster(void)
+{
+	unsigned long val;
+	int cpu = smp_processor_id();
+
+	apic_write(APIC_DFR, APIC_DFR_VALUE_CLUSTER);
+	val = calculate_ldr(cpu);
+	apic_write(APIC_LDR, val);
+}
+
 static inline void init_apic_ldr(void)
 {
 	unsigned long val;
@@ -70,10 +76,6 @@ static inline void init_apic_ldr(void)
 	apic_write(APIC_LDR, val);
 }
 
-#ifndef CONFIG_X86_GENERICARCH
-extern void enable_apic_mode(void);
-#endif
-
 extern int apic_version [MAX_APICS];
 static inline void setup_apic_routing(void)
 {
@@ -144,7 +146,7 @@ static inline int check_phys_apicid_present(int cpu_physical_apicid)
 	return (1);
 }
 
-static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+static inline unsigned int cpu_mask_to_apicid_cluster(cpumask_t cpumask)
 {
 	int num_bits_set;
 	int cpus_found = 0;
@@ -154,11 +156,7 @@ static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
 	num_bits_set = cpus_weight(cpumask);
 	/* Return id to all */
 	if (num_bits_set == NR_CPUS)
-#if defined CONFIG_ES7000_CLUSTERED_APIC
 		return 0xFF;
-#else
-		return cpu_to_logical_apicid(0);
-#endif
 	/*
 	 * The cpus in the mask must all be on the apic cluster.  If are not
 	 * on the same apicid cluster return default value of TARGET_CPUS.
@@ -171,11 +169,40 @@ static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
 			if (apicid_cluster(apicid) !=
 					apicid_cluster(new_apicid)){
 				printk ("%s: Not a valid mask!\n", __func__);
-#if defined CONFIG_ES7000_CLUSTERED_APIC
 				return 0xFF;
-#else
+			}
+			apicid = new_apicid;
+			cpus_found++;
+		}
+		cpu++;
+	}
+	return apicid;
+}
+
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+	int num_bits_set;
+	int cpus_found = 0;
+	int cpu;
+	int apicid;
+
+	num_bits_set = cpus_weight(cpumask);
+	/* Return id to all */
+	if (num_bits_set == NR_CPUS)
+		return cpu_to_logical_apicid(0);
+	/*
+	 * The cpus in the mask must all be on the apic cluster.  If are not
+	 * on the same apicid cluster return default value of TARGET_CPUS.
+	 */
+	cpu = first_cpu(cpumask);
+	apicid = cpu_to_logical_apicid(cpu);
+	while (cpus_found < num_bits_set) {
+		if (cpu_isset(cpu, cpumask)) {
+			int new_apicid = cpu_to_logical_apicid(cpu);
+			if (apicid_cluster(apicid) !=
+					apicid_cluster(new_apicid)){
+				printk ("%s: Not a valid mask!\n", __func__);
 				return cpu_to_logical_apicid(0);
-#endif
 			}
 			apicid = new_apicid;
 			cpus_found++;

arch/x86/include/asm/es7000/wakecpu.h

@@ -1,36 +1,12 @@
 #ifndef __ASM_ES7000_WAKECPU_H
 #define __ASM_ES7000_WAKECPU_H
 
-/*
- * This file copes with machines that wakeup secondary CPUs by the
- * INIT, INIT, STARTUP sequence.
- */
-
-#ifdef CONFIG_ES7000_CLUSTERED_APIC
-#define WAKE_SECONDARY_VIA_MIP
-#else
-#define WAKE_SECONDARY_VIA_INIT
-#endif
-
-#ifdef WAKE_SECONDARY_VIA_MIP
-extern int es7000_start_cpu(int cpu, unsigned long eip);
-static inline int
-wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
-{
-	int boot_error = 0;
-	boot_error = es7000_start_cpu(phys_apicid, start_eip);
-	return boot_error;
-}
-#endif
-
-#define TRAMPOLINE_LOW phys_to_virt(0x467)
-#define TRAMPOLINE_HIGH phys_to_virt(0x469)
-
-#define boot_cpu_apicid boot_cpu_physical_apicid
+#define TRAMPOLINE_PHYS_LOW	0x467
+#define TRAMPOLINE_PHYS_HIGH	0x469
 
 static inline void wait_for_init_deassert(atomic_t *deassert)
 {
-#ifdef WAKE_SECONDARY_VIA_INIT
+#ifndef CONFIG_ES7000_CLUSTERED_APIC
 	while (!atomic_read(deassert))
 		cpu_relax();
 #endif
@@ -50,9 +26,12 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
 {
 }
 
-#define inquire_remote_apic(apicid) do {		\
-		if (apic_verbosity >= APIC_DEBUG)	\
-			__inquire_remote_apic(apicid);	\
-	} while (0)
+extern void __inquire_remote_apic(int apicid);
+
+static inline void inquire_remote_apic(int apicid)
+{
+	if (apic_verbosity >= APIC_DEBUG)
+		__inquire_remote_apic(apicid);
+}
 
 #endif /* __ASM_MACH_WAKECPU_H */

arch/x86/include/asm/genapic_32.h

@@ -2,6 +2,7 @@
 #define _ASM_X86_GENAPIC_32_H
 
 #include <asm/mpspec.h>
+#include <asm/atomic.h>
 
 /*
  * Generic APIC driver interface.
@@ -65,6 +66,14 @@ struct genapic {
 	void (*send_IPI_allbutself)(int vector);
 	void (*send_IPI_all)(int vector);
 #endif
+	int (*wakeup_cpu)(int apicid, unsigned long start_eip);
+	int trampoline_phys_low;
+	int trampoline_phys_high;
+	void (*wait_for_init_deassert)(atomic_t *deassert);
+	void (*smp_callin_clear_local_apic)(void);
+	void (*store_NMI_vector)(unsigned short *high, unsigned short *low);
+	void (*restore_NMI_vector)(unsigned short *high, unsigned short *low);
+	void (*inquire_remote_apic)(int apicid);
 };
 
 #define APICFUNC(x) .x = x,
@@ -105,16 +114,24 @@ struct genapic {
 	APICFUNC(get_apic_id)				\
 	.apic_id_mask = APIC_ID_MASK,			\
 	APICFUNC(cpu_mask_to_apicid)			\
-	APICFUNC(vector_allocation_domain)			\
+	APICFUNC(vector_allocation_domain)		\
 	APICFUNC(acpi_madt_oem_check)			\
 	IPIFUNC(send_IPI_mask)				\
 	IPIFUNC(send_IPI_allbutself)			\
 	IPIFUNC(send_IPI_all)				\
 	APICFUNC(enable_apic_mode)			\
 	APICFUNC(phys_pkg_id)				\
+	.trampoline_phys_low = TRAMPOLINE_PHYS_LOW,		\
+	.trampoline_phys_high = TRAMPOLINE_PHYS_HIGH,		\
+	APICFUNC(wait_for_init_deassert)		\
+	APICFUNC(smp_callin_clear_local_apic)		\
+	APICFUNC(store_NMI_vector)			\
+	APICFUNC(restore_NMI_vector)			\
+	APICFUNC(inquire_remote_apic)			\
 }
 
 extern struct genapic *genapic;
+extern void es7000_update_genapic_to_cluster(void);
 
 enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
 #define get_uv_system_type()		UV_NONE

arch/x86/include/asm/genapic_64.h

@@ -32,6 +32,8 @@ struct genapic {
 	unsigned int (*get_apic_id)(unsigned long x);
 	unsigned long (*set_apic_id)(unsigned int id);
 	unsigned long apic_id_mask;
+	/* wakeup_secondary_cpu */
+	int (*wakeup_cpu)(int apicid, unsigned long start_eip);
 };
 
 extern struct genapic *genapic;

arch/x86/include/asm/hypervisor.h

@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2008, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#ifndef ASM_X86__HYPERVISOR_H
+#define ASM_X86__HYPERVISOR_H
+
+extern unsigned long get_hypervisor_tsc_freq(void);
+extern void init_hypervisor(struct cpuinfo_x86 *c);
+
+#endif

arch/x86/include/asm/ia32.h

@@ -129,24 +129,6 @@ typedef struct compat_siginfo {
 	} _sifields;
 } compat_siginfo_t;
 
-struct sigframe32 {
-	u32 pretcode;
-	int sig;
-	struct sigcontext_ia32 sc;
-	struct _fpstate_ia32 fpstate;
-	unsigned int extramask[_COMPAT_NSIG_WORDS-1];
-};
-
-struct rt_sigframe32 {
-	u32 pretcode;
-	int sig;
-	u32 pinfo;
-	u32 puc;
-	compat_siginfo_t info;
-	struct ucontext_ia32 uc;
-	struct _fpstate_ia32 fpstate;
-};
-
 struct ustat32 {
 	__u32			f_tfree;
 	compat_ino_t		f_tinode;

arch/x86/include/asm/idle.h

@@ -8,8 +8,13 @@ struct notifier_block;
 void idle_notifier_register(struct notifier_block *n);
 void idle_notifier_unregister(struct notifier_block *n);
 
+#ifdef CONFIG_X86_64
 void enter_idle(void);
 void exit_idle(void);
+#else /* !CONFIG_X86_64 */
+static inline void enter_idle(void) { }
+static inline void exit_idle(void) { }
+#endif /* CONFIG_X86_64 */
 
 void c1e_remove_cpu(int cpu);
 

arch/x86/include/asm/io.h

@@ -4,6 +4,7 @@
 #define ARCH_HAS_IOREMAP_WC
 
 #include <linux/compiler.h>
+#include <asm-generic/int-ll64.h>
 
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
@@ -45,20 +46,40 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
 #define mmiowb() barrier()
 
 #ifdef CONFIG_X86_64
+
 build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
-build_mmio_read(__readq, "q", unsigned long, "=r", )
 build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
-build_mmio_write(__writeq, "q", unsigned long, "r", )
 
-#define readq_relaxed(a) __readq(a)
-#define __raw_readq __readq
-#define __raw_writeq writeq
+#else
+
+static inline __u64 readq(const volatile void __iomem *addr)
+{
+	const volatile u32 __iomem *p = addr;
+	u32 low, high;
+
+	low = readl(p);
+	high = readl(p + 1);
+
+	return low + ((u64)high << 32);
+}
+
+static inline void writeq(__u64 val, volatile void __iomem *addr)
+{
+	writel(val, addr);
+	writel(val >> 32, addr+4);
+}
 
-/* Let people know we have them */
-#define readq readq
-#define writeq writeq
 #endif
 
+#define readq_relaxed(a)	readq(a)
+
+#define __raw_readq(a)		readq(a)
+#define __raw_writeq(val, addr)	writeq(val, addr)
+
+/* Let people know that we have them */
+#define readq			readq
+#define writeq			writeq
+
 extern int iommu_bio_merge;
 
 #ifdef CONFIG_X86_32

arch/x86/include/asm/io_apic.h

@@ -156,11 +156,21 @@ extern int sis_apic_bug;
 /* 1 if "noapic" boot option passed */
 extern int skip_ioapic_setup;
 
+/* 1 if "noapic" boot option passed */
+extern int noioapicquirk;
+
+/* -1 if "noapic" boot option passed */
+extern int noioapicreroute;
+
 /* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
 extern int timer_through_8259;
 
 static inline void disable_ioapic_setup(void)
 {
+#ifdef CONFIG_PCI
+	noioapicquirk = 1;
+	noioapicreroute = -1;
+#endif
 	skip_ioapic_setup = 1;
 }
 

arch/x86/include/asm/irq.h

@@ -31,10 +31,6 @@ static inline int irq_canonicalize(int irq)
 # endif
 #endif
 
-#ifdef CONFIG_IRQBALANCE
-extern int irqbalance_disable(char *str);
-#endif
-
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern void fixup_irqs(cpumask_t map);

arch/x86/include/asm/irq_regs_32.h

@@ -9,6 +9,8 @@
 
 #include <asm/percpu.h>
 
+#define ARCH_HAS_OWN_IRQ_REGS
+
 DECLARE_PER_CPU(struct pt_regs *, irq_regs);
 
 static inline struct pt_regs *get_irq_regs(void)

arch/x86/include/asm/kexec.h

@@ -5,21 +5,8 @@
 # define PA_CONTROL_PAGE	0
 # define VA_CONTROL_PAGE	1
 # define PA_PGD			2
-# define VA_PGD			3
-# define PA_PTE_0		4
-# define VA_PTE_0		5
-# define PA_PTE_1		6
-# define VA_PTE_1		7
-# define PA_SWAP_PAGE		8
-# ifdef CONFIG_X86_PAE
-#  define PA_PMD_0		9
-#  define VA_PMD_0		10
-#  define PA_PMD_1		11
-#  define VA_PMD_1		12
-#  define PAGES_NR		13
-# else
-#  define PAGES_NR		9
-# endif
+# define PA_SWAP_PAGE		3
+# define PAGES_NR		4
 #else
 # define PA_CONTROL_PAGE	0
 # define VA_CONTROL_PAGE	1
@@ -170,6 +157,20 @@ relocate_kernel(unsigned long indirection_page,
 		unsigned long start_address) ATTRIB_NORET;
 #endif
 
+#ifdef CONFIG_X86_32
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+	pgd_t *pgd;
+#ifdef CONFIG_X86_PAE
+	pmd_t *pmd0;
+	pmd_t *pmd1;
+#endif
+	pte_t *pte0;
+	pte_t *pte1;
+};
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_KEXEC_H */

arch/x86/include/asm/mach-default/mach_apic.h

@@ -32,11 +32,13 @@ static inline cpumask_t target_cpus(void)
 #define vector_allocation_domain    (genapic->vector_allocation_domain)
 #define read_apic_id()  (GET_APIC_ID(apic_read(APIC_ID)))
 #define send_IPI_self (genapic->send_IPI_self)
+#define wakeup_secondary_cpu (genapic->wakeup_cpu)
 extern void setup_apic_routing(void);
 #else
 #define INT_DELIVERY_MODE dest_LowestPrio
 #define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
 #define TARGET_CPUS (target_cpus())
+#define wakeup_secondary_cpu wakeup_secondary_cpu_via_init
 /*
  * Set up the logical destination ID.
  *

arch/x86/include/asm/mach-default/mach_wakecpu.h

@@ -1,17 +1,8 @@
 #ifndef _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H
 #define _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H
 
-/* 
- * This file copes with machines that wakeup secondary CPUs by the
- * INIT, INIT, STARTUP sequence.
- */
-
-#define WAKE_SECONDARY_VIA_INIT
-
-#define TRAMPOLINE_LOW phys_to_virt(0x467)
-#define TRAMPOLINE_HIGH phys_to_virt(0x469)
-
-#define boot_cpu_apicid boot_cpu_physical_apicid
+#define TRAMPOLINE_PHYS_LOW (0x467)
+#define TRAMPOLINE_PHYS_HIGH (0x469)
 
 static inline void wait_for_init_deassert(atomic_t *deassert)
 {
@@ -33,9 +24,12 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
 {
 }
 
-#define inquire_remote_apic(apicid) do {		\
-		if (apic_verbosity >= APIC_DEBUG)	\
-			__inquire_remote_apic(apicid);	\
-	} while (0)
+extern void __inquire_remote_apic(int apicid);
+
+static inline void inquire_remote_apic(int apicid)
+{
+	if (apic_verbosity >= APIC_DEBUG)
+		__inquire_remote_apic(apicid);
+}
 
 #endif /* _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H */

arch/x86/include/asm/mach-default/smpboot_hooks.h

@@ -13,9 +13,11 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 	CMOS_WRITE(0xa, 0xf);
 	local_flush_tlb();
 	pr_debug("1.\n");
-	*((volatile unsigned short *) TRAMPOLINE_HIGH) = start_eip >> 4;
+	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
+								 start_eip >> 4;
 	pr_debug("2.\n");
-	*((volatile unsigned short *) TRAMPOLINE_LOW) = start_eip & 0xf;
+	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
+							 start_eip & 0xf;
 	pr_debug("3.\n");
 }
 
@@ -32,7 +34,7 @@ static inline void smpboot_restore_warm_reset_vector(void)
 	 */
 	CMOS_WRITE(0, 0xf);
 
-	*((volatile long *) phys_to_virt(0x467)) = 0;
+	*((volatile long *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
 }
 
 static inline void __init smpboot_setup_io_apic(void)

arch/x86/include/asm/mach-generic/mach_apic.h

@@ -27,6 +27,7 @@
 #define vector_allocation_domain (genapic->vector_allocation_domain)
 #define enable_apic_mode (genapic->enable_apic_mode)
 #define phys_pkg_id (genapic->phys_pkg_id)
+#define wakeup_secondary_cpu (genapic->wakeup_cpu)
 
 extern void generic_bigsmp_probe(void);
 

arch/x86/include/asm/mach-generic/mach_wakecpu.h

@@ -0,0 +1,12 @@
+#ifndef _ASM_X86_MACH_GENERIC_MACH_WAKECPU_H
+#define _ASM_X86_MACH_GENERIC_MACH_WAKECPU_H
+
+#define TRAMPOLINE_PHYS_LOW (genapic->trampoline_phys_low)
+#define TRAMPOLINE_PHYS_HIGH (genapic->trampoline_phys_high)
+#define wait_for_init_deassert (genapic->wait_for_init_deassert)
+#define smp_callin_clear_local_apic (genapic->smp_callin_clear_local_apic)
+#define store_NMI_vector (genapic->store_NMI_vector)
+#define restore_NMI_vector (genapic->restore_NMI_vector)
+#define inquire_remote_apic (genapic->inquire_remote_apic)
+
+#endif /* _ASM_X86_MACH_GENERIC_MACH_APIC_H */

arch/x86/include/asm/mmu_context_32.h

@@ -4,9 +4,8 @@
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 #ifdef CONFIG_SMP
-	unsigned cpu = smp_processor_id();
-	if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
-		per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_LAZY;
+	if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK)
+		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_LAZY);
 #endif
 }
 
@@ -20,8 +19,8 @@ static inline void switch_mm(struct mm_struct *prev,
 		/* stop flush ipis for the previous mm */
 		cpu_clear(cpu, prev->cpu_vm_mask);
 #ifdef CONFIG_SMP
-		per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
-		per_cpu(cpu_tlbstate, cpu).active_mm = next;
+		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
+		x86_write_percpu(cpu_tlbstate.active_mm, next);
 #endif
 		cpu_set(cpu, next->cpu_vm_mask);
 
@@ -36,8 +35,8 @@ static inline void switch_mm(struct mm_struct *prev,
 	}
 #ifdef CONFIG_SMP
 	else {
-		per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
-		BUG_ON(per_cpu(cpu_tlbstate, cpu).active_mm != next);
+		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
+		BUG_ON(x86_read_percpu(cpu_tlbstate.active_mm) != next);
 
 		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
 			/* We were in lazy tlb mode and leave_mm disabled

arch/x86/include/asm/msr-index.h

@@ -85,7 +85,9 @@
 /* AMD64 MSRs. Not complete. See the architecture manual for a more
    complete list. */
 
+#define MSR_AMD64_PATCH_LEVEL		0x0000008b
 #define MSR_AMD64_NB_CFG		0xc001001f
+#define MSR_AMD64_PATCH_LOADER		0xc0010020
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030
 #define MSR_AMD64_IBSFETCHLINAD		0xc0011031
 #define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032

arch/x86/include/asm/msr.h

@@ -22,10 +22,10 @@ static inline unsigned long long native_read_tscp(unsigned int *aux)
 }
 
 /*
- * i386 calling convention returns 64-bit value in edx:eax, while
- * x86_64 returns at rax. Also, the "A" constraint does not really
- * mean rdx:rax in x86_64, so we need specialized behaviour for each
- * architecture
+ * both i386 and x86_64 returns 64-bit value in edx:eax, but gcc's "A"
+ * constraint has different meanings. For i386, "A" means exactly
+ * edx:eax, while for x86_64 it doesn't mean rdx:rax or edx:eax. Instead,
+ * it means rax *or* rdx.
  */
 #ifdef CONFIG_X86_64
 #define DECLARE_ARGS(val, low, high)	unsigned low, high
@@ -181,10 +181,10 @@ static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 }
 
 #define rdtscl(low)						\
-	((low) = (u32)native_read_tsc())
+	((low) = (u32)__native_read_tsc())
 
 #define rdtscll(val)						\
-	((val) = native_read_tsc())
+	((val) = __native_read_tsc())
 
 #define rdpmc(counter, low, high)			\
 do {							\

arch/x86/include/asm/numaq/wakecpu.h

@@ -3,12 +3,8 @@
 
 /* This file copes with machines that wakeup secondary CPUs by NMIs */
 
-#define WAKE_SECONDARY_VIA_NMI
-
-#define TRAMPOLINE_LOW phys_to_virt(0x8)
-#define TRAMPOLINE_HIGH phys_to_virt(0xa)
-
-#define boot_cpu_apicid boot_cpu_logical_apicid
+#define TRAMPOLINE_PHYS_LOW (0x8)
+#define TRAMPOLINE_PHYS_HIGH (0xa)
 
 /* We don't do anything here because we use NMI's to boot instead */
 static inline void wait_for_init_deassert(atomic_t *deassert)
@@ -27,17 +23,23 @@ static inline void smp_callin_clear_local_apic(void)
 static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
 {
 	printk("Storing NMI vector\n");
-	*high = *((volatile unsigned short *) TRAMPOLINE_HIGH);
-	*low = *((volatile unsigned short *) TRAMPOLINE_LOW);
+	*high =
+	  *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH));
+	*low =
+	  *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW));
 }
 
 static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
 {
 	printk("Restoring NMI vector\n");
-	*((volatile unsigned short *) TRAMPOLINE_HIGH) = *high;
-	*((volatile unsigned short *) TRAMPOLINE_LOW) = *low;
+	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
+								 *high;
+	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
+								 *low;
 }
 
-#define inquire_remote_apic(apicid) {}
+static inline void inquire_remote_apic(int apicid)
+{
+}
 
 #endif /* __ASM_NUMAQ_WAKECPU_H */

arch/x86/include/asm/pci.h

@@ -19,6 +19,8 @@ struct pci_sysdata {
 };
 
 extern int pci_routeirq;
+extern int noioapicquirk;
+extern int noioapicreroute;
 
 /* scan a bus after allocating a pci_sysdata for it */
 extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops,

arch/x86/include/asm/pgtable-2level.h

@@ -56,23 +56,55 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #define pte_none(x)		(!(x).pte_low)
 
 /*
- * Bits 0, 6 and 7 are taken, split up the 29 bits of offset
- * into this range:
+ * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
+ * split up the 29 bits of offset into this range:
  */
 #define PTE_FILE_MAX_BITS	29
+#define PTE_FILE_SHIFT1		(_PAGE_BIT_PRESENT + 1)
+#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
+#define PTE_FILE_SHIFT2		(_PAGE_BIT_FILE + 1)
+#define PTE_FILE_SHIFT3		(_PAGE_BIT_PROTNONE + 1)
+#else
+#define PTE_FILE_SHIFT2		(_PAGE_BIT_PROTNONE + 1)
+#define PTE_FILE_SHIFT3		(_PAGE_BIT_FILE + 1)
+#endif
+#define PTE_FILE_BITS1		(PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1)
+#define PTE_FILE_BITS2		(PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
 
 #define pte_to_pgoff(pte)						\
-	((((pte).pte_low >> 1) & 0x1f) + (((pte).pte_low >> 8) << 5))
+	((((pte).pte_low >> PTE_FILE_SHIFT1)				\
+	  & ((1U << PTE_FILE_BITS1) - 1))				\
+	 + ((((pte).pte_low >> PTE_FILE_SHIFT2)				\
+	     & ((1U << PTE_FILE_BITS2) - 1)) << PTE_FILE_BITS1)		\
+	 + (((pte).pte_low >> PTE_FILE_SHIFT3)				\
+	    << (PTE_FILE_BITS1 + PTE_FILE_BITS2)))
 
 #define pgoff_to_pte(off)						\
-	((pte_t) { .pte_low = (((off) & 0x1f) << 1) +			\
-			(((off) >> 5) << 8) + _PAGE_FILE })
+	((pte_t) { .pte_low =						\
+	 (((off) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1)	\
+	 + ((((off) >> PTE_FILE_BITS1) & ((1U << PTE_FILE_BITS2) - 1))	\
+	    << PTE_FILE_SHIFT2)						\
+	 + (((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2))		\
+	    << PTE_FILE_SHIFT3)						\
+	 + _PAGE_FILE })
 
 /* Encode and de-code a swap entry */
-#define __swp_type(x)			(((x).val >> 1) & 0x1f)
-#define __swp_offset(x)			((x).val >> 8)
-#define __swp_entry(type, offset)				\
-	((swp_entry_t) { ((type) << 1) | ((offset) << 8) })
+#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
+#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
+#else
+#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1)
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1)
+#endif
+
+#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
+
+#define __swp_type(x)			(((x).val >> (_PAGE_BIT_PRESENT + 1)) \
+					 & ((1U << SWP_TYPE_BITS) - 1))
+#define __swp_offset(x)			((x).val >> SWP_OFFSET_SHIFT)
+#define __swp_entry(type, offset)	((swp_entry_t) { \
+					 ((type) << (_PAGE_BIT_PRESENT + 1)) \
+					 | ((offset) << SWP_OFFSET_SHIFT) })
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
 

arch/x86/include/asm/pgtable-3level.h

@@ -166,6 +166,7 @@ static inline int pte_none(pte_t pte)
 #define PTE_FILE_MAX_BITS       32
 
 /* Encode and de-code a swap entry */
+#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5)
 #define __swp_type(x)			(((x).val) & 0x1f)
 #define __swp_offset(x)			((x).val >> 5)
 #define __swp_entry(type, offset)	((swp_entry_t){(type) | (offset) << 5})

arch/x86/include/asm/pgtable.h

@@ -10,7 +10,6 @@
 #define _PAGE_BIT_PCD		4	/* page cache disabled */
 #define _PAGE_BIT_ACCESSED	5	/* was accessed (raised by CPU) */
 #define _PAGE_BIT_DIRTY		6	/* was written to (raised by CPU) */
-#define _PAGE_BIT_FILE		6
 #define _PAGE_BIT_PSE		7	/* 4 MB (or 2MB) page */
 #define _PAGE_BIT_PAT		7	/* on 4KB pages */
 #define _PAGE_BIT_GLOBAL	8	/* Global TLB entry PPro+ */
@@ -22,6 +21,12 @@
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_UNUSED1
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
 
+/* If _PAGE_BIT_PRESENT is clear, we use these: */
+/* - if the user mapped it with PROT_NONE; pte_present gives true */
+#define _PAGE_BIT_PROTNONE	_PAGE_BIT_GLOBAL
+/* - set: nonlinear file mapping, saved PTE; unset:swap */
+#define _PAGE_BIT_FILE		_PAGE_BIT_DIRTY
+
 #define _PAGE_PRESENT	(_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
 #define _PAGE_RW	(_AT(pteval_t, 1) << _PAGE_BIT_RW)
 #define _PAGE_USER	(_AT(pteval_t, 1) << _PAGE_BIT_USER)
@@ -46,11 +51,8 @@
 #define _PAGE_NX	(_AT(pteval_t, 0))
 #endif
 
-/* If _PAGE_PRESENT is clear, we use these: */
-#define _PAGE_FILE	_PAGE_DIRTY	/* nonlinear file mapping,
-					 * saved PTE; unset:swap */
-#define _PAGE_PROTNONE	_PAGE_PSE	/* if the user mapped it with PROT_NONE;
-					   pte_present gives true */
+#define _PAGE_FILE	(_AT(pteval_t, 1) << _PAGE_BIT_FILE)
+#define _PAGE_PROTNONE	(_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
 
 #define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |	\
 			 _PAGE_ACCESSED | _PAGE_DIRTY)
@@ -158,8 +160,19 @@
 #define PGD_IDENT_ATTR	 0x001		/* PRESENT (no other attributes) */
 #endif
 
+/*
+ * Macro to mark a page protection value as UC-
+ */
+#define pgprot_noncached(prot)					\
+	((boot_cpu_data.x86 > 3)				\
+	 ? (__pgprot(pgprot_val(prot) | _PAGE_CACHE_UC_MINUS))	\
+	 : (prot))
+
 #ifndef __ASSEMBLY__
 
+#define pgprot_writecombine	pgprot_writecombine
+extern pgprot_t pgprot_writecombine(pgprot_t prot);
+
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
@@ -329,6 +342,9 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
 
 #ifndef __ASSEMBLY__
+/* Indicate that x86 has its own track and untrack pfn vma functions */
+#define __HAVE_PFNMAP_TRACKING
+
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 struct file;
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,

arch/x86/include/asm/pgtable_32.h

@@ -100,15 +100,6 @@ extern unsigned long pg0[];
 # include <asm/pgtable-2level.h>
 #endif
 
-/*
- * Macro to mark a page protection value as "uncacheable".
- * On processors which do not support it, this is a no-op.
- */
-#define pgprot_noncached(prot)					\
-	((boot_cpu_data.x86 > 3)				\
-	 ? (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT))	\
-	 : (prot))
-
 /*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.

arch/x86/include/asm/pgtable_64.h

@@ -146,7 +146,7 @@ static inline void native_pgd_clear(pgd_t *pgd)
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
 
-#define MAXMEM		 _AC(0x00003fffffffffff, UL)
+#define MAXMEM		 _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
 #define VMALLOC_START    _AC(0xffffc20000000000, UL)
 #define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
 #define VMEMMAP_START	 _AC(0xffffe20000000000, UL)
@@ -176,12 +176,6 @@ static inline int pmd_bad(pmd_t pmd)
 
 #define pages_to_mb(x)	((x) >> (20 - PAGE_SHIFT))   /* FIXME: is this right? */
 
-/*
- * Macro to mark a page protection value as "uncacheable".
- */
-#define pgprot_noncached(prot)					\
-	(__pgprot(pgprot_val((prot)) | _PAGE_PCD | _PAGE_PWT))
-
 /*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
@@ -250,10 +244,22 @@ static inline int pud_large(pud_t pte)
 extern int direct_gbpages;
 
 /* Encode and de-code a swap entry */
-#define __swp_type(x)			(((x).val >> 1) & 0x3f)
-#define __swp_offset(x)			((x).val >> 8)
-#define __swp_entry(type, offset)	((swp_entry_t) { ((type) << 1) | \
-							 ((offset) << 8) })
+#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
+#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
+#else
+#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1)
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1)
+#endif
+
+#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
+
+#define __swp_type(x)			(((x).val >> (_PAGE_BIT_PRESENT + 1)) \
+					 & ((1U << SWP_TYPE_BITS) - 1))
+#define __swp_offset(x)			((x).val >> SWP_OFFSET_SHIFT)
+#define __swp_entry(type, offset)	((swp_entry_t) { \
+					 ((type) << (_PAGE_BIT_PRESENT + 1)) \
+					 | ((offset) << SWP_OFFSET_SHIFT) })
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
 

arch/x86/include/asm/prctl.h

@@ -6,5 +6,8 @@
 #define ARCH_GET_FS 0x1003
 #define ARCH_GET_GS 0x1004
 
+#ifdef CONFIG_X86_64
+extern long sys_arch_prctl(int, unsigned long);
+#endif /* CONFIG_X86_64 */
 
 #endif /* _ASM_X86_PRCTL_H */

arch/x86/include/asm/processor.h

@@ -110,6 +110,7 @@ struct cpuinfo_x86 {
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 #endif
+	unsigned int		x86_hyper_vendor;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 #define X86_VENDOR_INTEL	0
@@ -123,6 +124,9 @@ struct cpuinfo_x86 {
 
 #define X86_VENDOR_UNKNOWN	0xff
 
+#define X86_HYPER_VENDOR_NONE  0
+#define X86_HYPER_VENDOR_VMWARE 1
+
 /*
  * capabilities of CPUs
  */

arch/x86/include/asm/reboot.h

@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_REBOOT_H
 #define _ASM_X86_REBOOT_H
 
+#include <linux/kdebug.h>
+
 struct pt_regs;
 
 struct machine_ops {
@@ -18,4 +20,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs);
 void native_machine_shutdown(void);
 void machine_real_restart(const unsigned char *code, int length);
 
+typedef void (*nmi_shootdown_cb)(int, struct die_args*);
+void nmi_shootdown_cpus(nmi_shootdown_cb callback);
+
 #endif /* _ASM_X86_REBOOT_H */

arch/x86/include/asm/setup.h

@@ -8,6 +8,10 @@
 /* Interrupt control for vSMPowered x86_64 systems */
 void vsmp_init(void);
 
+
+void setup_bios_corruption_check(void);
+
+
 #ifdef CONFIG_X86_VISWS
 extern void visws_early_detect(void);
 extern int is_visws_box(void);
@@ -16,6 +20,8 @@ static inline void visws_early_detect(void) { }
 static inline int is_visws_box(void) { return 0; }
 #endif
 
+extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
+extern int wakeup_secondary_cpu_via_init(int apicid, unsigned long start_eip);
 /*
  * Any setup quirks to be performed?
  */
@@ -39,6 +45,7 @@ struct x86_quirks {
 	void (*smp_read_mpc_oem)(struct mp_config_oemtable *oemtable,
                                     unsigned short oemsize);
 	int (*setup_ioapic_ids)(void);
+	int (*update_genapic)(void);
 };
 
 extern struct x86_quirks *x86_quirks;

arch/x86/include/asm/sigframe.h

@@ -0,0 +1,70 @@
+#ifndef _ASM_X86_SIGFRAME_H
+#define _ASM_X86_SIGFRAME_H
+
+#include <asm/sigcontext.h>
+#include <asm/siginfo.h>
+#include <asm/ucontext.h>
+
+#ifdef CONFIG_X86_32
+#define sigframe_ia32		sigframe
+#define rt_sigframe_ia32	rt_sigframe
+#define sigcontext_ia32		sigcontext
+#define _fpstate_ia32		_fpstate
+#define ucontext_ia32		ucontext
+#else /* !CONFIG_X86_32 */
+
+#ifdef CONFIG_IA32_EMULATION
+#include <asm/ia32.h>
+#endif /* CONFIG_IA32_EMULATION */
+
+#endif /* CONFIG_X86_32 */
+
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+struct sigframe_ia32 {
+	u32 pretcode;
+	int sig;
+	struct sigcontext_ia32 sc;
+	/*
+	 * fpstate is unused. fpstate is moved/allocated after
+	 * retcode[] below. This movement allows to have the FP state and the
+	 * future state extensions (xsave) stay together.
+	 * And at the same time retaining the unused fpstate, prevents changing
+	 * the offset of extramask[] in the sigframe and thus prevent any
+	 * legacy application accessing/modifying it.
+	 */
+	struct _fpstate_ia32 fpstate_unused;
+#ifdef CONFIG_IA32_EMULATION
+	unsigned int extramask[_COMPAT_NSIG_WORDS-1];
+#else /* !CONFIG_IA32_EMULATION */
+	unsigned long extramask[_NSIG_WORDS-1];
+#endif /* CONFIG_IA32_EMULATION */
+	char retcode[8];
+	/* fp state follows here */
+};
+
+struct rt_sigframe_ia32 {
+	u32 pretcode;
+	int sig;
+	u32 pinfo;
+	u32 puc;
+#ifdef CONFIG_IA32_EMULATION
+	compat_siginfo_t info;
+#else /* !CONFIG_IA32_EMULATION */
+	struct siginfo info;
+#endif /* CONFIG_IA32_EMULATION */
+	struct ucontext_ia32 uc;
+	char retcode[8];
+	/* fp state follows here */
+};
+#endif /* defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) */
+
+#ifdef CONFIG_X86_64
+struct rt_sigframe {
+	char __user *pretcode;
+	struct ucontext uc;
+	struct siginfo info;
+	/* fp state follows here */
+};
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_SIGFRAME_H */

arch/x86/include/asm/signal.h

@@ -121,6 +121,10 @@ typedef unsigned long sigset_t;
 
 #ifndef __ASSEMBLY__
 
+# ifdef __KERNEL__
+extern void do_notify_resume(struct pt_regs *, void *, __u32);
+# endif /* __KERNEL__ */
+
 #ifdef __i386__
 # ifdef __KERNEL__
 struct old_sigaction {
@@ -141,8 +145,6 @@ struct k_sigaction {
 	struct sigaction sa;
 };
 
-extern void do_notify_resume(struct pt_regs *, void *, __u32);
-
 # else /* __KERNEL__ */
 /* Here we must cater to libcs that poke about in kernel headers.  */
 

arch/x86/include/asm/sparsemem.h

@@ -27,7 +27,7 @@
 #else /* CONFIG_X86_32 */
 # define SECTION_SIZE_BITS	27 /* matt - 128 is convenient right now */
 # define MAX_PHYSADDR_BITS	44
-# define MAX_PHYSMEM_BITS	44
+# define MAX_PHYSMEM_BITS	44 /* Can be max 45 bits */
 #endif
 
 #endif /* CONFIG_SPARSEMEM */

arch/x86/include/asm/syscalls.h

@@ -19,6 +19,13 @@
 /* kernel/ioport.c */
 asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
 
+/* kernel/ldt.c */
+asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
+
+/* kernel/tls.c */
+asmlinkage int sys_set_thread_area(struct user_desc __user *);
+asmlinkage int sys_get_thread_area(struct user_desc __user *);
+
 /* X86_32 only */
 #ifdef CONFIG_X86_32
 /* kernel/process_32.c */
@@ -33,14 +40,11 @@ asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
 			     struct old_sigaction __user *);
 asmlinkage int sys_sigaltstack(unsigned long);
 asmlinkage unsigned long sys_sigreturn(unsigned long);
-asmlinkage int sys_rt_sigreturn(unsigned long);
+asmlinkage int sys_rt_sigreturn(struct pt_regs);
 
 /* kernel/ioport.c */
 asmlinkage long sys_iopl(unsigned long);
 
-/* kernel/ldt.c */
-asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
-
 /* kernel/sys_i386_32.c */
 asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
 			  unsigned long, unsigned long, unsigned long);
@@ -54,10 +58,6 @@ asmlinkage int sys_uname(struct old_utsname __user *);
 struct oldold_utsname;
 asmlinkage int sys_olduname(struct oldold_utsname __user *);
 
-/* kernel/tls.c */
-asmlinkage int sys_set_thread_area(struct user_desc __user *);
-asmlinkage int sys_get_thread_area(struct user_desc __user *);
-
 /* kernel/vm86_32.c */
 asmlinkage int sys_vm86old(struct pt_regs);
 asmlinkage int sys_vm86(struct pt_regs);

arch/x86/include/asm/system.h

@@ -17,12 +17,12 @@
 # define AT_VECTOR_SIZE_ARCH 1
 #endif
 
-#ifdef CONFIG_X86_32
-
 struct task_struct; /* one of the stranger aspects of C forward declarations */
 struct task_struct *__switch_to(struct task_struct *prev,
 				struct task_struct *next);
 
+#ifdef CONFIG_X86_32
+
 /*
  * Saving eflags is important. It switches not only IOPL between tasks,
  * it also protects other tasks from NT leaking through sysenter etc.
@@ -314,6 +314,8 @@ extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
 
 void default_idle(void);
 
+void stop_this_cpu(void *dummy);
+
 /*
  * Force strict CPU ordering.
  * And yes, this is required on UP too when we're talking

arch/x86/include/asm/thread_info.h

@@ -24,7 +24,7 @@ struct exec_domain;
 struct thread_info {
 	struct task_struct	*task;		/* main task structure */
 	struct exec_domain	*exec_domain;	/* execution domain */
-	unsigned long		flags;		/* low level flags */
+	__u32			flags;		/* low level flags */
 	__u32			status;		/* thread synchronous flags */
 	__u32			cpu;		/* current CPU */
 	int			preempt_count;	/* 0 => preemptable,

arch/x86/include/asm/trampoline.h

@@ -3,6 +3,7 @@
 
 #ifndef __ASSEMBLY__
 
+#ifdef CONFIG_X86_TRAMPOLINE
 /*
  * Trampoline 80x86 program as an array.
  */
@@ -13,8 +14,14 @@ extern unsigned char *trampoline_base;
 extern unsigned long init_rsp;
 extern unsigned long initial_code;
 
+#define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
 #define TRAMPOLINE_BASE 0x6000
+
 extern unsigned long setup_trampoline(void);
+extern void __init reserve_trampoline_memory(void);
+#else
+static inline void reserve_trampoline_memory(void) {};
+#endif /* CONFIG_X86_TRAMPOLINE */
 
 #endif /* __ASSEMBLY__ */
 

arch/x86/include/asm/traps.h

@@ -46,6 +46,10 @@ dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *, long);
 dotraplinkage void do_invalid_TSS(struct pt_regs *, long);
 dotraplinkage void do_segment_not_present(struct pt_regs *, long);
 dotraplinkage void do_stack_segment(struct pt_regs *, long);
+#ifdef CONFIG_X86_64
+dotraplinkage void do_double_fault(struct pt_regs *, long);
+asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *);
+#endif
 dotraplinkage void do_general_protection(struct pt_regs *, long);
 dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
 dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long);
@@ -72,10 +76,13 @@ static inline int get_si_code(unsigned long condition)
 extern int panic_on_unrecovered_nmi;
 extern int kstack_depth_to_print;
 
-#ifdef CONFIG_X86_32
 void math_error(void __user *);
-unsigned long patch_espfix_desc(unsigned long, unsigned long);
 asmlinkage void math_emulate(long);
+#ifdef CONFIG_X86_32
+unsigned long patch_espfix_desc(unsigned long, unsigned long);
+#else
+asmlinkage void smp_thermal_interrupt(void);
+asmlinkage void mce_threshold_interrupt(void);
 #endif
 
 #endif /* _ASM_X86_TRAPS_H */

arch/x86/include/asm/tsc.h

@@ -34,8 +34,6 @@ static inline cycles_t get_cycles(void)
 
 static __always_inline cycles_t vget_cycles(void)
 {
-	cycles_t cycles;
-
 	/*
 	 * We only do VDSOs on TSC capable CPUs, so this shouldnt
 	 * access boot_cpu_data (which is not VDSO-safe):
@@ -44,11 +42,7 @@ static __always_inline cycles_t vget_cycles(void)
 	if (!cpu_has_tsc)
 		return 0;
 #endif
-	rdtsc_barrier();
-	cycles = (cycles_t)__native_read_tsc();
-	rdtsc_barrier();
-
-	return cycles;
+	return (cycles_t)__native_read_tsc();
 }
 
 extern void tsc_init(void);

arch/x86/include/asm/uaccess.h

@@ -350,14 +350,14 @@ do {									\
 
 #define __put_user_nocheck(x, ptr, size)			\
 ({								\
-	long __pu_err;						\
+	int __pu_err;						\
 	__put_user_size((x), (ptr), (size), __pu_err, -EFAULT);	\
 	__pu_err;						\
 })
 
 #define __get_user_nocheck(x, ptr, size)				\
 ({									\
-	long __gu_err;							\
+	int __gu_err;							\
 	unsigned long __gu_val;						\
 	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\

arch/x86/include/asm/uv/bios.h

@@ -32,13 +32,18 @@
 enum uv_bios_cmd {
 	UV_BIOS_COMMON,
 	UV_BIOS_GET_SN_INFO,
-	UV_BIOS_FREQ_BASE
+	UV_BIOS_FREQ_BASE,
+	UV_BIOS_WATCHLIST_ALLOC,
+	UV_BIOS_WATCHLIST_FREE,
+	UV_BIOS_MEMPROTECT,
+	UV_BIOS_GET_PARTITION_ADDR
 };
 
 /*
  * Status values returned from a BIOS call.
  */
 enum {
+	BIOS_STATUS_MORE_PASSES		=  1,
 	BIOS_STATUS_SUCCESS		=  0,
 	BIOS_STATUS_UNIMPLEMENTED	= -ENOSYS,
 	BIOS_STATUS_EINVAL		= -EINVAL,
@@ -71,6 +76,21 @@ union partition_info_u {
 	};
 };
 
+union uv_watchlist_u {
+	u64	val;
+	struct {
+		u64	blade	: 16,
+			size	: 32,
+			filler	: 16;
+	};
+};
+
+enum uv_memprotect {
+	UV_MEMPROT_RESTRICT_ACCESS,
+	UV_MEMPROT_ALLOW_AMO,
+	UV_MEMPROT_ALLOW_RW
+};
+
 /*
  * bios calls have 6 parameters
  */
@@ -80,14 +100,20 @@ extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64);
 
 extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *);
 extern s64 uv_bios_freq_base(u64, u64 *);
+extern int uv_bios_mq_watchlist_alloc(int, unsigned long, unsigned int,
+					unsigned long *);
+extern int uv_bios_mq_watchlist_free(int, int);
+extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect);
+extern s64 uv_bios_reserved_page_pa(u64, u64 *, u64 *, u64 *);
 
 extern void uv_bios_init(void);
 
+extern unsigned long sn_rtc_cycles_per_second;
 extern int uv_type;
 extern long sn_partition_id;
-extern long uv_coherency_id;
-extern long uv_region_size;
-#define partition_coherence_id()	(uv_coherency_id)
+extern long sn_coherency_id;
+extern long sn_region_size;
+#define partition_coherence_id()	(sn_coherency_id)
 
 extern struct kobject *sgi_uv_kobj;	/* /sys/firmware/sgi_uv */
 

arch/x86/include/asm/uv/uv_hub.h

@@ -113,25 +113,37 @@
  */
 #define UV_MAX_NASID_VALUE	(UV_MAX_NUMALINK_NODES * 2)
 
+struct uv_scir_s {
+	struct timer_list timer;
+	unsigned long	offset;
+	unsigned long	last;
+	unsigned long	idle_on;
+	unsigned long	idle_off;
+	unsigned char	state;
+	unsigned char	enabled;
+};
+
 /*
  * The following defines attributes of the HUB chip. These attributes are
  * frequently referenced and are kept in the per-cpu data areas of each cpu.
  * They are kept together in a struct to minimize cache misses.
  */
 struct uv_hub_info_s {
-	unsigned long	global_mmr_base;
-	unsigned long	gpa_mask;
-	unsigned long	gnode_upper;
-	unsigned long	lowmem_remap_top;
-	unsigned long	lowmem_remap_base;
-	unsigned short	pnode;
-	unsigned short	pnode_mask;
-	unsigned short	coherency_domain_number;
-	unsigned short	numa_blade_id;
-	unsigned char	blade_processor_id;
-	unsigned char	m_val;
-	unsigned char	n_val;
+	unsigned long		global_mmr_base;
+	unsigned long		gpa_mask;
+	unsigned long		gnode_upper;
+	unsigned long		lowmem_remap_top;
+	unsigned long		lowmem_remap_base;
+	unsigned short		pnode;
+	unsigned short		pnode_mask;
+	unsigned short		coherency_domain_number;
+	unsigned short		numa_blade_id;
+	unsigned char		blade_processor_id;
+	unsigned char		m_val;
+	unsigned char		n_val;
+	struct uv_scir_s	scir;
 };
+
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define uv_hub_info 		(&__get_cpu_var(__uv_hub_info))
 #define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
@@ -163,6 +175,30 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 
 #define UV_APIC_PNODE_SHIFT	6
 
+/* Local Bus from cpu's perspective */
+#define LOCAL_BUS_BASE		0x1c00000
+#define LOCAL_BUS_SIZE		(4 * 1024 * 1024)
+
+/*
+ * System Controller Interface Reg
+ *
+ * Note there are NO leds on a UV system.  This register is only
+ * used by the system controller to monitor system-wide operation.
+ * There are 64 regs per node.  With Nahelem cpus (2 cores per node,
+ * 8 cpus per core, 2 threads per cpu) there are 32 cpu threads on
+ * a node.
+ *
+ * The window is located at top of ACPI MMR space
+ */
+#define SCIR_WINDOW_COUNT	64
+#define SCIR_LOCAL_MMR_BASE	(LOCAL_BUS_BASE + \
+				 LOCAL_BUS_SIZE - \
+				 SCIR_WINDOW_COUNT)
+
+#define SCIR_CPU_HEARTBEAT	0x01	/* timer interrupt */
+#define SCIR_CPU_ACTIVITY	0x02	/* not idle */
+#define SCIR_CPU_HB_INTERVAL	(HZ)	/* once per second */
+
 /*
  * Macros for converting between kernel virtual addresses, socket local physical
  * addresses, and UV global physical addresses.
@@ -174,7 +210,7 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
 {
 	if (paddr < uv_hub_info->lowmem_remap_top)
-		paddr += uv_hub_info->lowmem_remap_base;
+		paddr |= uv_hub_info->lowmem_remap_base;
 	return paddr | uv_hub_info->gnode_upper;
 }
 
@@ -182,19 +218,7 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
 /* socket virtual --> UV global physical address */
 static inline unsigned long uv_gpa(void *v)
 {
-	return __pa(v) | uv_hub_info->gnode_upper;
-}
-
-/* socket virtual --> UV global physical address */
-static inline void *uv_vgpa(void *v)
-{
-	return (void *)uv_gpa(v);
-}
-
-/* UV global physical address --> socket virtual */
-static inline void *uv_va(unsigned long gpa)
-{
-	return __va(gpa & uv_hub_info->gpa_mask);
+	return uv_soc_phys_ram_to_gpa(__pa(v));
 }
 
 /* pnode, offset --> socket virtual */
@@ -277,6 +301,16 @@ static inline void uv_write_local_mmr(unsigned long offset, unsigned long val)
 	*uv_local_mmr_address(offset) = val;
 }
 
+static inline unsigned char uv_read_local_mmr8(unsigned long offset)
+{
+	return *((unsigned char *)uv_local_mmr_address(offset));
+}
+
+static inline void uv_write_local_mmr8(unsigned long offset, unsigned char val)
+{
+	*((unsigned char *)uv_local_mmr_address(offset)) = val;
+}
+
 /*
  * Structures and definitions for converting between cpu, node, pnode, and blade
  * numbers.
@@ -351,5 +385,20 @@ static inline int uv_num_possible_blades(void)
 	return uv_possible_blades;
 }
 
-#endif /* _ASM_X86_UV_UV_HUB_H */
+/* Update SCIR state */
+static inline void uv_set_scir_bits(unsigned char value)
+{
+	if (uv_hub_info->scir.state != value) {
+		uv_hub_info->scir.state = value;
+		uv_write_local_mmr8(uv_hub_info->scir.offset, value);
+	}
+}
+static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
+{
+	if (uv_cpu_hub_info(cpu)->scir.state != value) {
+		uv_cpu_hub_info(cpu)->scir.state = value;
+		uv_write_local_mmr8(uv_cpu_hub_info(cpu)->scir.offset, value);
+	}
+}
 
+#endif /* _ASM_X86_UV_UV_HUB_H */

arch/x86/include/asm/vmware.h

@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2008, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#ifndef ASM_X86__VMWARE_H
+#define ASM_X86__VMWARE_H
+
+extern unsigned long vmware_get_tsc_khz(void);
+extern int vmware_platform(void);
+extern void vmware_set_feature_bits(struct cpuinfo_x86 *c);
+
+#endif

arch/x86/include/asm/xen/hypercall.h

@@ -33,8 +33,14 @@
 #ifndef _ASM_X86_XEN_HYPERCALL_H
 #define _ASM_X86_XEN_HYPERCALL_H
 
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/types.h>
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>

arch/x86/include/asm/xen/hypervisor.h

@@ -33,39 +33,10 @@
 #ifndef _ASM_X86_XEN_HYPERVISOR_H
 #define _ASM_X86_XEN_HYPERVISOR_H
 
-#include <linux/types.h>
-#include <linux/kernel.h>
-
-#include <xen/interface/xen.h>
-#include <xen/interface/version.h>
-
-#include <asm/ptrace.h>
-#include <asm/page.h>
-#include <asm/desc.h>
-#if defined(__i386__)
-#  ifdef CONFIG_X86_PAE
-#   include <asm-generic/pgtable-nopud.h>
-#  else
-#   include <asm-generic/pgtable-nopmd.h>
-#  endif
-#endif
-#include <asm/xen/hypercall.h>
-
 /* arch/i386/kernel/setup.c */
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
-/* arch/i386/mach-xen/evtchn.c */
-/* Force a proper event-channel callback from Xen. */
-extern void force_evtchn_callback(void);
-
-/* Turn jiffies into Xen system time. */
-u64 jiffies_to_st(unsigned long jiffies);
-
-
-#define MULTI_UVMFLAGS_INDEX 3
-#define MULTI_UVMDOMID_INDEX 4
-
 enum xen_domain_type {
 	XEN_NATIVE,
 	XEN_PV_DOMAIN,
@@ -74,9 +45,15 @@ enum xen_domain_type {
 
 extern enum xen_domain_type xen_domain_type;
 
+#ifdef CONFIG_XEN
 #define xen_domain()		(xen_domain_type != XEN_NATIVE)
-#define xen_pv_domain()		(xen_domain_type == XEN_PV_DOMAIN)
+#else
+#define xen_domain()		(0)
+#endif
+
+#define xen_pv_domain()		(xen_domain() && xen_domain_type == XEN_PV_DOMAIN)
+#define xen_hvm_domain()	(xen_domain() && xen_domain_type == XEN_HVM_DOMAIN)
+
 #define xen_initial_domain()	(xen_pv_domain() && xen_start_info->flags & SIF_INITDOMAIN)
-#define xen_hvm_domain()	(xen_domain_type == XEN_HVM_DOMAIN)
 
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */

arch/x86/include/asm/xen/page.h

@@ -1,11 +1,16 @@
 #ifndef _ASM_X86_XEN_PAGE_H
 #define _ASM_X86_XEN_PAGE_H
 
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
 #include <linux/pfn.h>
 
 #include <asm/uaccess.h>
+#include <asm/page.h>
 #include <asm/pgtable.h>
 
+#include <xen/interface/xen.h>
 #include <xen/features.h>
 
 /* Xen machine address */

arch/x86/kernel/Makefile

@@ -12,6 +12,7 @@ CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
 #
@@ -23,9 +24,9 @@ CFLAGS_vsyscall_64.o	:= $(PROFILING) -g0 $(nostackp)
 CFLAGS_hpet.o		:= $(nostackp)
 CFLAGS_tsc.o		:= $(nostackp)
 
-obj-y			:= process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
+obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
-obj-y			+= time_$(BITS).o ioport.o ldt.o
+obj-y			+= time_$(BITS).o ioport.o ldt.o dumpstack.o
 obj-y			+= setup.o i8259.o irqinit_$(BITS).o setup_percpu.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
@@ -105,6 +106,8 @@ microcode-$(CONFIG_MICROCODE_INTEL)	+= microcode_intel.o
 microcode-$(CONFIG_MICROCODE_AMD)	+= microcode_amd.o
 obj-$(CONFIG_MICROCODE)			+= microcode.o
 
+obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
+
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)

arch/x86/kernel/acpi/boot.c

@@ -1360,6 +1360,17 @@ static void __init acpi_process_madt(void)
 			disable_acpi();
 		}
 	}
+
+	/*
+	 * ACPI supports both logical (e.g. Hyper-Threading) and physical
+	 * processors, where MPS only supports physical.
+	 */
+	if (acpi_lapic && acpi_ioapic)
+		printk(KERN_INFO "Using ACPI (MADT) for SMP configuration "
+		       "information\n");
+	else if (acpi_lapic)
+		printk(KERN_INFO "Using ACPI for processor (LAPIC) "
+		       "configuration information\n");
 #endif
 	return;
 }

arch/x86/kernel/apic.c

@@ -441,6 +441,7 @@ static void lapic_timer_setup(enum clock_event_mode mode,
 		v = apic_read(APIC_LVTT);
 		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
 		apic_write(APIC_LVTT, v);
+		apic_write(APIC_TMICT, 0xffffffff);
 		break;
 	case CLOCK_EVT_MODE_RESUME:
 		/* Nothing to do here */
@@ -559,13 +560,13 @@ static int __init calibrate_by_pmtimer(long deltapm, long *delta)
 	} else {
 		res = (((u64)deltapm) *  mult) >> 22;
 		do_div(res, 1000000);
-		printk(KERN_WARNING "APIC calibration not consistent "
+		pr_warning("APIC calibration not consistent "
 			"with PM Timer: %ldms instead of 100ms\n",
 			(long)res);
 		/* Correct the lapic counter value */
 		res = (((u64)(*delta)) * pm_100ms);
 		do_div(res, deltapm);
-		printk(KERN_INFO "APIC delta adjusted to PM-Timer: "
+		pr_info("APIC delta adjusted to PM-Timer: "
 			"%lu (%ld)\n", (unsigned long)res, *delta);
 		*delta = (long)res;
 	}
@@ -645,8 +646,7 @@ static int __init calibrate_APIC_clock(void)
 	 */
 	if (calibration_result < (1000000 / HZ)) {
 		local_irq_enable();
-		printk(KERN_WARNING
-		       "APIC frequency too slow, disabling apic timer\n");
+		pr_warning("APIC frequency too slow, disabling apic timer\n");
 		return -1;
 	}
 
@@ -672,13 +672,9 @@ static int __init calibrate_APIC_clock(void)
 		while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
 			cpu_relax();
 
-		local_irq_disable();
-
 		/* Stop the lapic timer */
 		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, levt);
 
-		local_irq_enable();
-
 		/* Jiffies delta */
 		deltaj = lapic_cal_j2 - lapic_cal_j1;
 		apic_printk(APIC_VERBOSE, "... jiffies delta = %lu\n", deltaj);
@@ -692,8 +688,7 @@ static int __init calibrate_APIC_clock(void)
 		local_irq_enable();
 
 	if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
-		printk(KERN_WARNING
-		       "APIC timer disabled due to verification failure.\n");
+		pr_warning("APIC timer disabled due to verification failure.\n");
 			return -1;
 	}
 
@@ -714,7 +709,7 @@ void __init setup_boot_APIC_clock(void)
 	 * broadcast mechanism is used. On UP systems simply ignore it.
 	 */
 	if (disable_apic_timer) {
-		printk(KERN_INFO "Disabling APIC timer\n");
+		pr_info("Disabling APIC timer\n");
 		/* No broadcast on UP ! */
 		if (num_possible_cpus() > 1) {
 			lapic_clockevent.mult = 1;
@@ -741,7 +736,7 @@ void __init setup_boot_APIC_clock(void)
 	if (nmi_watchdog != NMI_IO_APIC)
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
 	else
-		printk(KERN_WARNING "APIC timer registered as dummy,"
+		pr_warning("APIC timer registered as dummy,"
 			" due to nmi_watchdog=%d!\n", nmi_watchdog);
 
 	/* Setup the lapic or request the broadcast */
@@ -773,8 +768,7 @@ static void local_apic_timer_interrupt(void)
 	 * spurious.
 	 */
 	if (!evt->event_handler) {
-		printk(KERN_WARNING
-		       "Spurious LAPIC timer interrupt on cpu %d\n", cpu);
+		pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", cpu);
 		/* Switch it off */
 		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
 		return;
@@ -814,9 +808,7 @@ void smp_apic_timer_interrupt(struct pt_regs *regs)
 	 * Besides, if we don't timer interrupts ignore the global
 	 * interrupt lock, which is the WrongThing (tm) to do.
 	 */
-#ifdef CONFIG_X86_64
 	exit_idle();
-#endif
 	irq_enter();
 	local_apic_timer_interrupt();
 	irq_exit();
@@ -1093,7 +1085,7 @@ static void __cpuinit lapic_setup_esr(void)
 	unsigned int oldvalue, value, maxlvt;
 
 	if (!lapic_is_integrated()) {
-		printk(KERN_INFO "No ESR for 82489DX.\n");
+		pr_info("No ESR for 82489DX.\n");
 		return;
 	}
 
@@ -1104,7 +1096,7 @@ static void __cpuinit lapic_setup_esr(void)
 		 * ESR disabled - we can't do anything useful with the
 		 * errors anyway - mbligh
 		 */
-		printk(KERN_INFO "Leaving ESR disabled.\n");
+		pr_info("Leaving ESR disabled.\n");
 		return;
 	}
 
@@ -1298,7 +1290,7 @@ void check_x2apic(void)
 	rdmsr(MSR_IA32_APICBASE, msr, msr2);
 
 	if (msr & X2APIC_ENABLE) {
-		printk("x2apic enabled by BIOS, switching to x2apic ops\n");
+		pr_info("x2apic enabled by BIOS, switching to x2apic ops\n");
 		x2apic_preenabled = x2apic = 1;
 		apic_ops = &x2apic_ops;
 	}
@@ -1310,7 +1302,7 @@ void enable_x2apic(void)
 
 	rdmsr(MSR_IA32_APICBASE, msr, msr2);
 	if (!(msr & X2APIC_ENABLE)) {
-		printk("Enabling x2apic\n");
+		pr_info("Enabling x2apic\n");
 		wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
 	}
 }
@@ -1325,9 +1317,8 @@ void __init enable_IR_x2apic(void)
 		return;
 
 	if (!x2apic_preenabled && disable_x2apic) {
-		printk(KERN_INFO
-		       "Skipped enabling x2apic and Interrupt-remapping "
-		       "because of nox2apic\n");
+		pr_info("Skipped enabling x2apic and Interrupt-remapping "
+			"because of nox2apic\n");
 		return;
 	}
 
@@ -1335,22 +1326,19 @@ void __init enable_IR_x2apic(void)
 		panic("Bios already enabled x2apic, can't enforce nox2apic");
 
 	if (!x2apic_preenabled && skip_ioapic_setup) {
-		printk(KERN_INFO
-		       "Skipped enabling x2apic and Interrupt-remapping "
-		       "because of skipping io-apic setup\n");
+		pr_info("Skipped enabling x2apic and Interrupt-remapping "
+			"because of skipping io-apic setup\n");
 		return;
 	}
 
 	ret = dmar_table_init();
 	if (ret) {
-		printk(KERN_INFO
-		       "dmar_table_init() failed with %d:\n", ret);
+		pr_info("dmar_table_init() failed with %d:\n", ret);
 
 		if (x2apic_preenabled)
 			panic("x2apic enabled by bios. But IR enabling failed");
 		else
-			printk(KERN_INFO
-			       "Not enabling x2apic,Intr-remapping\n");
+			pr_info("Not enabling x2apic,Intr-remapping\n");
 		return;
 	}
 
@@ -1359,7 +1347,7 @@ void __init enable_IR_x2apic(void)
 
 	ret = save_mask_IO_APIC_setup();
 	if (ret) {
-		printk(KERN_INFO "Saving IO-APIC state failed: %d\n", ret);
+		pr_info("Saving IO-APIC state failed: %d\n", ret);
 		goto end;
 	}
 
@@ -1394,14 +1382,11 @@ end:
 
 	if (!ret) {
 		if (!x2apic_preenabled)
-			printk(KERN_INFO
-			       "Enabled x2apic and interrupt-remapping\n");
+			pr_info("Enabled x2apic and interrupt-remapping\n");
 		else
-			printk(KERN_INFO
-			       "Enabled Interrupt-remapping\n");
+			pr_info("Enabled Interrupt-remapping\n");
 	} else
-		printk(KERN_ERR
-		       "Failed to enable Interrupt-remapping and x2apic\n");
+		pr_err("Failed to enable Interrupt-remapping and x2apic\n");
 #else
 	if (!cpu_has_x2apic)
 		return;
@@ -1410,8 +1395,8 @@ end:
 		panic("x2apic enabled prior OS handover,"
 		      " enable CONFIG_INTR_REMAP");
 
-	printk(KERN_INFO "Enable CONFIG_INTR_REMAP for enabling intr-remapping "
-	       " and x2apic\n");
+	pr_info("Enable CONFIG_INTR_REMAP for enabling intr-remapping "
+		" and x2apic\n");
 #endif
 
 	return;
@@ -1428,7 +1413,7 @@ end:
 static int __init detect_init_APIC(void)
 {
 	if (!cpu_has_apic) {
-		printk(KERN_INFO "No local APIC present\n");
+		pr_info("No local APIC present\n");
 		return -1;
 	}
 
@@ -1469,8 +1454,8 @@ static int __init detect_init_APIC(void)
 		 * "lapic" specified.
 		 */
 		if (!force_enable_local_apic) {
-			printk(KERN_INFO "Local APIC disabled by BIOS -- "
-			       "you can enable it with \"lapic\"\n");
+			pr_info("Local APIC disabled by BIOS -- "
+				"you can enable it with \"lapic\"\n");
 			return -1;
 		}
 		/*
@@ -1480,8 +1465,7 @@ static int __init detect_init_APIC(void)
 		 */
 		rdmsr(MSR_IA32_APICBASE, l, h);
 		if (!(l & MSR_IA32_APICBASE_ENABLE)) {
-			printk(KERN_INFO
-			       "Local APIC disabled by BIOS -- reenabling.\n");
+			pr_info("Local APIC disabled by BIOS -- reenabling.\n");
 			l &= ~MSR_IA32_APICBASE_BASE;
 			l |= MSR_IA32_APICBASE_ENABLE | APIC_DEFAULT_PHYS_BASE;
 			wrmsr(MSR_IA32_APICBASE, l, h);
@@ -1494,7 +1478,7 @@ static int __init detect_init_APIC(void)
 	 */
 	features = cpuid_edx(1);
 	if (!(features & (1 << X86_FEATURE_APIC))) {
-		printk(KERN_WARNING "Could not enable APIC!\n");
+		pr_warning("Could not enable APIC!\n");
 		return -1;
 	}
 	set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
@@ -1505,14 +1489,14 @@ static int __init detect_init_APIC(void)
 	if (l & MSR_IA32_APICBASE_ENABLE)
 		mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
 
-	printk(KERN_INFO "Found and enabled local APIC!\n");
+	pr_info("Found and enabled local APIC!\n");
 
 	apic_pm_activate();
 
 	return 0;
 
 no_apic:
-	printk(KERN_INFO "No local APIC present or hardware disabled\n");
+	pr_info("No local APIC present or hardware disabled\n");
 	return -1;
 }
 #endif
@@ -1588,12 +1572,12 @@ int __init APIC_init_uniprocessor(void)
 {
 #ifdef CONFIG_X86_64
 	if (disable_apic) {
-		printk(KERN_INFO "Apic disabled\n");
+		pr_info("Apic disabled\n");
 		return -1;
 	}
 	if (!cpu_has_apic) {
 		disable_apic = 1;
-		printk(KERN_INFO "Apic disabled by BIOS\n");
+		pr_info("Apic disabled by BIOS\n");
 		return -1;
 	}
 #else
@@ -1605,8 +1589,8 @@ int __init APIC_init_uniprocessor(void)
 	 */
 	if (!cpu_has_apic &&
 	    APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
-		printk(KERN_ERR "BIOS bug, local APIC 0x%x not detected!...\n",
-		       boot_cpu_physical_apicid);
+		pr_err("BIOS bug, local APIC 0x%x not detected!...\n",
+			boot_cpu_physical_apicid);
 		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
 		return -1;
 	}
@@ -1682,9 +1666,7 @@ void smp_spurious_interrupt(struct pt_regs *regs)
 {
 	u32 v;
 
-#ifdef CONFIG_X86_64
 	exit_idle();
-#endif
 	irq_enter();
 	/*
 	 * Check if this really is a spurious interrupt and ACK it
@@ -1699,8 +1681,8 @@ void smp_spurious_interrupt(struct pt_regs *regs)
 	add_pda(irq_spurious_count, 1);
 #else
 	/* see sw-dev-man vol 3, chapter 7.4.13.5 */
-	printk(KERN_INFO "spurious APIC interrupt on CPU#%d, "
-	       "should never happen.\n", smp_processor_id());
+	pr_info("spurious APIC interrupt on CPU#%d, "
+		"should never happen.\n", smp_processor_id());
 	__get_cpu_var(irq_stat).irq_spurious_count++;
 #endif
 	irq_exit();
@@ -1713,9 +1695,7 @@ void smp_error_interrupt(struct pt_regs *regs)
 {
 	u32 v, v1;
 
-#ifdef CONFIG_X86_64
 	exit_idle();
-#endif
 	irq_enter();
 	/* First tickle the hardware, only then report what went on. -- REW */
 	v = apic_read(APIC_ESR);
@@ -1724,17 +1704,18 @@ void smp_error_interrupt(struct pt_regs *regs)
 	ack_APIC_irq();
 	atomic_inc(&irq_err_count);
 
-	/* Here is what the APIC error bits mean:
-	   0: Send CS error
-	   1: Receive CS error
-	   2: Send accept error
-	   3: Receive accept error
-	   4: Reserved
-	   5: Send illegal vector
-	   6: Received illegal vector
-	   7: Illegal register address
-	*/
-	printk(KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n",
+	/*
+	 * Here is what the APIC error bits mean:
+	 * 0: Send CS error
+	 * 1: Receive CS error
+	 * 2: Send accept error
+	 * 3: Receive accept error
+	 * 4: Reserved
+	 * 5: Send illegal vector
+	 * 6: Received illegal vector
+	 * 7: Illegal register address
+	 */
+	pr_debug("APIC error on CPU%d: %02x(%02x)\n",
 		smp_processor_id(), v , v1);
 	irq_exit();
 }
@@ -1838,15 +1819,15 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	 * Validate version
 	 */
 	if (version == 0x0) {
-		printk(KERN_WARNING "BIOS bug, APIC version is 0 for CPU#%d! "
-				"fixing up to 0x10. (tell your hw vendor)\n",
-				version);
+		pr_warning("BIOS bug, APIC version is 0 for CPU#%d! "
+			"fixing up to 0x10. (tell your hw vendor)\n",
+			version);
 		version = 0x10;
 	}
 	apic_version[apicid] = version;
 
 	if (num_processors >= NR_CPUS) {
-		printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached."
+		pr_warning("WARNING: NR_CPUS limit of %i reached."
 			"  Processor ignored.\n", NR_CPUS);
 		return;
 	}
@@ -2209,7 +2190,7 @@ static int __init apic_set_verbosity(char *arg)
 	else if (strcmp("verbose", arg) == 0)
 		apic_verbosity = APIC_VERBOSE;
 	else {
-		printk(KERN_WARNING "APIC Verbosity level %s not recognised"
+		pr_warning("APIC Verbosity level %s not recognised"
 			" use apic=verbose or apic=debug\n", arg);
 		return -EINVAL;
 	}

arch/x86/kernel/apm_32.c

@@ -391,11 +391,7 @@ static int power_off;
 #else
 static int power_off = 1;
 #endif
-#ifdef CONFIG_APM_REAL_MODE_POWER_OFF
-static int realmode_power_off = 1;
-#else
 static int realmode_power_off;
-#endif
 #ifdef CONFIG_APM_ALLOW_INTS
 static int allow_ints = 1;
 #else

arch/x86/kernel/asm-offsets_32.c

@@ -11,7 +11,7 @@
 #include <linux/suspend.h>
 #include <linux/kbuild.h>
 #include <asm/ucontext.h>
-#include "sigframe.h"
+#include <asm/sigframe.h>
 #include <asm/pgtable.h>
 #include <asm/fixmap.h>
 #include <asm/processor.h>

arch/x86/kernel/asm-offsets_64.c

@@ -20,6 +20,8 @@
 
 #include <xen/interface/xen.h>
 
+#include <asm/sigframe.h>
+
 #define __NO_STUBS 1
 #undef __SYSCALL
 #undef _ASM_X86_UNISTD_64_H
@@ -87,7 +89,7 @@ int main(void)
 	BLANK();
 #undef ENTRY
 	DEFINE(IA32_RT_SIGFRAME_sigcontext,
-	       offsetof (struct rt_sigframe32, uc.uc_mcontext));
+	       offsetof (struct rt_sigframe_ia32, uc.uc_mcontext));
 	BLANK();
 #endif
 	DEFINE(pbe_address, offsetof(struct pbe, address));

arch/x86/kernel/bios_uv.c

@@ -69,10 +69,10 @@ s64 uv_bios_call_reentrant(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
 
 long sn_partition_id;
 EXPORT_SYMBOL_GPL(sn_partition_id);
-long uv_coherency_id;
-EXPORT_SYMBOL_GPL(uv_coherency_id);
-long uv_region_size;
-EXPORT_SYMBOL_GPL(uv_region_size);
+long sn_coherency_id;
+EXPORT_SYMBOL_GPL(sn_coherency_id);
+long sn_region_size;
+EXPORT_SYMBOL_GPL(sn_region_size);
 int uv_type;
 
 
@@ -100,6 +100,56 @@ s64 uv_bios_get_sn_info(int fc, int *uvtype, long *partid, long *coher,
 	return ret;
 }
 
+int
+uv_bios_mq_watchlist_alloc(int blade, unsigned long addr, unsigned int mq_size,
+			   unsigned long *intr_mmr_offset)
+{
+	union uv_watchlist_u size_blade;
+	u64 watchlist;
+	s64 ret;
+
+	size_blade.size = mq_size;
+	size_blade.blade = blade;
+
+	/*
+	 * bios returns watchlist number or negative error number.
+	 */
+	ret = (int)uv_bios_call_irqsave(UV_BIOS_WATCHLIST_ALLOC, addr,
+			size_blade.val, (u64)intr_mmr_offset,
+			(u64)&watchlist, 0);
+	if (ret < BIOS_STATUS_SUCCESS)
+		return ret;
+
+	return watchlist;
+}
+EXPORT_SYMBOL_GPL(uv_bios_mq_watchlist_alloc);
+
+int
+uv_bios_mq_watchlist_free(int blade, int watchlist_num)
+{
+	return (int)uv_bios_call_irqsave(UV_BIOS_WATCHLIST_FREE,
+				blade, watchlist_num, 0, 0, 0);
+}
+EXPORT_SYMBOL_GPL(uv_bios_mq_watchlist_free);
+
+s64
+uv_bios_change_memprotect(u64 paddr, u64 len, enum uv_memprotect perms)
+{
+	return uv_bios_call_irqsave(UV_BIOS_MEMPROTECT, paddr, len,
+					perms, 0, 0);
+}
+EXPORT_SYMBOL_GPL(uv_bios_change_memprotect);
+
+s64
+uv_bios_reserved_page_pa(u64 buf, u64 *cookie, u64 *addr, u64 *len)
+{
+	s64 ret;
+
+	ret = uv_bios_call_irqsave(UV_BIOS_GET_PARTITION_ADDR, (u64)cookie,
+					(u64)addr, buf, (u64)len, 0);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(uv_bios_reserved_page_pa);
 
 s64 uv_bios_freq_base(u64 clock_type, u64 *ticks_per_second)
 {

arch/x86/kernel/check.c

@@ -0,0 +1,161 @@
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/kthread.h>
+#include <linux/workqueue.h>
+#include <asm/e820.h>
+#include <asm/proto.h>
+
+/*
+ * 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.
+ */
+#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 __init 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 __init 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 __init 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);
+
+
+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();
+}
+
+
+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_ONCE(corruption, KERN_ERR "Memory corruption detected in low memory\n");
+}
+
+static void check_corruption(struct work_struct *dummy);
+static DECLARE_DELAYED_WORK(bios_check_work, check_corruption);
+
+static void check_corruption(struct work_struct *dummy)
+{
+	check_for_bios_corruption();
+	schedule_delayed_work(&bios_check_work,
+		round_jiffies_relative(corruption_check_period*HZ)); 
+}
+
+static int start_periodic_check_for_corruption(void)
+{
+	if (!memory_corruption_check || corruption_check_period == 0)
+		return 0;
+
+	printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n",
+	       corruption_check_period);
+
+	/* First time we run the checks right away */
+	schedule_delayed_work(&bios_check_work, 0);
+	return 0;
+}
+
+module_init(start_periodic_check_for_corruption);
+

arch/x86/kernel/cpu/Makefile

@@ -4,6 +4,7 @@
 
 obj-y			:= intel_cacheinfo.o addon_cpuid_features.o
 obj-y			+= proc.o capflags.o powerflags.o common.o
+obj-y			+= vmware.o hypervisor.o
 
 obj-$(CONFIG_X86_32)	+= bugs.o cmpxchg.o
 obj-$(CONFIG_X86_64)	+= bugs_64.o

arch/x86/kernel/cpu/common.c

@@ -36,6 +36,7 @@
 #include <asm/proto.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/hypervisor.h>
 
 #include "cpu.h"
 
@@ -703,6 +704,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 	detect_ht(c);
 #endif
 
+	init_hypervisor(c);
 	/*
 	 * On SMP, boot_cpu_data holds the common feature set between
 	 * all CPUs; so make sure that we indicate which features are
@@ -862,7 +864,7 @@ EXPORT_SYMBOL(_cpu_pda);
 
 struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
 
-char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
+static char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
 
 void __cpuinit pda_init(int cpu)
 {
@@ -903,8 +905,8 @@ void __cpuinit pda_init(int cpu)
 	}
 }
 
-char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
-			   DEBUG_STKSZ] __page_aligned_bss;
+static char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
+				  DEBUG_STKSZ] __page_aligned_bss;
 
 extern asmlinkage void ignore_sysret(void);
 

arch/x86/kernel/cpu/hypervisor.c

@@ -0,0 +1,58 @@
+/*
+ * Common hypervisor code
+ *
+ * Copyright (C) 2008, VMware, Inc.
+ * Author : Alok N Kataria <akataria@vmware.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+
+#include <asm/processor.h>
+#include <asm/vmware.h>
+#include <asm/hypervisor.h>
+
+static inline void __cpuinit
+detect_hypervisor_vendor(struct cpuinfo_x86 *c)
+{
+	if (vmware_platform()) {
+		c->x86_hyper_vendor = X86_HYPER_VENDOR_VMWARE;
+	} else {
+		c->x86_hyper_vendor = X86_HYPER_VENDOR_NONE;
+	}
+}
+
+unsigned long get_hypervisor_tsc_freq(void)
+{
+	if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE)
+		return vmware_get_tsc_khz();
+	return 0;
+}
+
+static inline void __cpuinit
+hypervisor_set_feature_bits(struct cpuinfo_x86 *c)
+{
+	if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE) {
+		vmware_set_feature_bits(c);
+		return;
+	}
+}
+
+void __cpuinit init_hypervisor(struct cpuinfo_x86 *c)
+{
+	detect_hypervisor_vendor(c);
+	hypervisor_set_feature_bits(c);
+}

arch/x86/kernel/cpu/intel.c

@@ -307,12 +307,11 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_P4);
 	if (c->x86 == 6)
 		set_cpu_cap(c, X86_FEATURE_P3);
+#endif
 
 	if (cpu_has_bts)
 		ptrace_bts_init_intel(c);
 
-#endif
-
 	detect_extended_topology(c);
 	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
 		/*

arch/x86/kernel/cpu/intel_cacheinfo.c

@@ -644,20 +644,17 @@ static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf)
 	return show_shared_cpu_map_func(leaf, 1, buf);
 }
 
-static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf) {
-	switch(this_leaf->eax.split.type) {
-	    case CACHE_TYPE_DATA:
+static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
+{
+	switch (this_leaf->eax.split.type) {
+	case CACHE_TYPE_DATA:
 		return sprintf(buf, "Data\n");
-		break;
-	    case CACHE_TYPE_INST:
+	case CACHE_TYPE_INST:
 		return sprintf(buf, "Instruction\n");
-		break;
-	    case CACHE_TYPE_UNIFIED:
+	case CACHE_TYPE_UNIFIED:
 		return sprintf(buf, "Unified\n");
-		break;
-	    default:
+	default:
 		return sprintf(buf, "Unknown\n");
-		break;
 	}
 }
 

arch/x86/kernel/cpu/mtrr/main.c

@@ -803,6 +803,7 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 }
 
 static struct res_range __initdata range[RANGE_NUM];
+static int __initdata nr_range;
 
 #ifdef CONFIG_MTRR_SANITIZER
 
@@ -1206,39 +1207,43 @@ struct mtrr_cleanup_result {
 #define PSHIFT		(PAGE_SHIFT - 10)
 
 static struct mtrr_cleanup_result __initdata result[NUM_RESULT];
-static struct res_range __initdata range_new[RANGE_NUM];
 static unsigned long __initdata min_loss_pfn[RANGE_NUM];
 
-static int __init mtrr_cleanup(unsigned address_bits)
+static void __init print_out_mtrr_range_state(void)
 {
-	unsigned long extra_remove_base, extra_remove_size;
-	unsigned long base, size, def, dummy;
-	mtrr_type type;
-	int nr_range, nr_range_new;
-	u64 chunk_size, gran_size;
-	unsigned long range_sums, range_sums_new;
-	int index_good;
-	int num_reg_good;
 	int i;
+	char start_factor = 'K', size_factor = 'K';
+	unsigned long start_base, size_base;
+	mtrr_type type;
 
-	/* extra one for all 0 */
-	int num[MTRR_NUM_TYPES + 1];
+	for (i = 0; i < num_var_ranges; i++) {
 
-	if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
-		return 0;
-	rdmsr(MTRRdefType_MSR, def, dummy);
-	def &= 0xff;
-	if (def != MTRR_TYPE_UNCACHABLE)
-		return 0;
+		size_base = range_state[i].size_pfn << (PAGE_SHIFT - 10);
+		if (!size_base)
+			continue;
 
-	/* get it and store it aside */
-	memset(range_state, 0, sizeof(range_state));
-	for (i = 0; i < num_var_ranges; i++) {
-		mtrr_if->get(i, &base, &size, &type);
-		range_state[i].base_pfn = base;
-		range_state[i].size_pfn = size;
-		range_state[i].type = type;
+		size_base = to_size_factor(size_base, &size_factor),
+		start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10);
+		start_base = to_size_factor(start_base, &start_factor),
+		type = range_state[i].type;
+
+		printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
+			i, start_base, start_factor,
+			size_base, size_factor,
+			(type == MTRR_TYPE_UNCACHABLE) ? "UC" :
+			    ((type == MTRR_TYPE_WRPROT) ? "WP" :
+			     ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other"))
+			);
 	}
+}
+
+static int __init mtrr_need_cleanup(void)
+{
+	int i;
+	mtrr_type type;
+	unsigned long size;
+	/* extra one for all 0 */
+	int num[MTRR_NUM_TYPES + 1];
 
 	/* check entries number */
 	memset(num, 0, sizeof(num));
@@ -1263,29 +1268,133 @@ static int __init mtrr_cleanup(unsigned address_bits)
 		num_var_ranges - num[MTRR_NUM_TYPES])
 		return 0;
 
-	/* print original var MTRRs at first, for debugging: */
-	printk(KERN_DEBUG "original variable MTRRs\n");
-	for (i = 0; i < num_var_ranges; i++) {
-		char start_factor = 'K', size_factor = 'K';
-		unsigned long start_base, size_base;
+	return 1;
+}
 
-		size_base = range_state[i].size_pfn << (PAGE_SHIFT - 10);
-		if (!size_base)
-			continue;
+static unsigned long __initdata range_sums;
+static void __init mtrr_calc_range_state(u64 chunk_size, u64 gran_size,
+					 unsigned long extra_remove_base,
+					 unsigned long extra_remove_size,
+					 int i)
+{
+	int num_reg;
+	static struct res_range range_new[RANGE_NUM];
+	static int nr_range_new;
+	unsigned long range_sums_new;
+
+	/* convert ranges to var ranges state */
+	num_reg = x86_setup_var_mtrrs(range, nr_range,
+						chunk_size, gran_size);
+
+	/* we got new setting in range_state, check it */
+	memset(range_new, 0, sizeof(range_new));
+	nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
+				extra_remove_base, extra_remove_size);
+	range_sums_new = sum_ranges(range_new, nr_range_new);
+
+	result[i].chunk_sizek = chunk_size >> 10;
+	result[i].gran_sizek = gran_size >> 10;
+	result[i].num_reg = num_reg;
+	if (range_sums < range_sums_new) {
+		result[i].lose_cover_sizek =
+			(range_sums_new - range_sums) << PSHIFT;
+		result[i].bad = 1;
+	} else
+		result[i].lose_cover_sizek =
+			(range_sums - range_sums_new) << PSHIFT;
 
-		size_base = to_size_factor(size_base, &size_factor),
-		start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10);
-		start_base = to_size_factor(start_base, &start_factor),
-		type = range_state[i].type;
+	/* double check it */
+	if (!result[i].bad && !result[i].lose_cover_sizek) {
+		if (nr_range_new != nr_range ||
+			memcmp(range, range_new, sizeof(range)))
+				result[i].bad = 1;
+	}
 
-		printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
-			i, start_base, start_factor,
-			size_base, size_factor,
-			(type == MTRR_TYPE_UNCACHABLE) ? "UC" :
-			    ((type == MTRR_TYPE_WRPROT) ? "WP" :
-			     ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other"))
-			);
+	if (!result[i].bad && (range_sums - range_sums_new <
+				min_loss_pfn[num_reg])) {
+		min_loss_pfn[num_reg] =
+			range_sums - range_sums_new;
 	}
+}
+
+static void __init mtrr_print_out_one_result(int i)
+{
+	char gran_factor, chunk_factor, lose_factor;
+	unsigned long gran_base, chunk_base, lose_base;
+
+	gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
+	chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
+	lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
+	printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
+			result[i].bad ? "*BAD*" : " ",
+			gran_base, gran_factor, chunk_base, chunk_factor);
+	printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
+			result[i].num_reg, result[i].bad ? "-" : "",
+			lose_base, lose_factor);
+}
+
+static int __init mtrr_search_optimal_index(void)
+{
+	int i;
+	int num_reg_good;
+	int index_good;
+
+	if (nr_mtrr_spare_reg >= num_var_ranges)
+		nr_mtrr_spare_reg = num_var_ranges - 1;
+	num_reg_good = -1;
+	for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) {
+		if (!min_loss_pfn[i])
+			num_reg_good = i;
+	}
+
+	index_good = -1;
+	if (num_reg_good != -1) {
+		for (i = 0; i < NUM_RESULT; i++) {
+			if (!result[i].bad &&
+			    result[i].num_reg == num_reg_good &&
+			    !result[i].lose_cover_sizek) {
+				index_good = i;
+				break;
+			}
+		}
+	}
+
+	return index_good;
+}
+
+
+static int __init mtrr_cleanup(unsigned address_bits)
+{
+	unsigned long extra_remove_base, extra_remove_size;
+	unsigned long base, size, def, dummy;
+	mtrr_type type;
+	u64 chunk_size, gran_size;
+	int index_good;
+	int i;
+
+	if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
+		return 0;
+	rdmsr(MTRRdefType_MSR, def, dummy);
+	def &= 0xff;
+	if (def != MTRR_TYPE_UNCACHABLE)
+		return 0;
+
+	/* get it and store it aside */
+	memset(range_state, 0, sizeof(range_state));
+	for (i = 0; i < num_var_ranges; i++) {
+		mtrr_if->get(i, &base, &size, &type);
+		range_state[i].base_pfn = base;
+		range_state[i].size_pfn = size;
+		range_state[i].type = type;
+	}
+
+	/* check if we need handle it and can handle it */
+	if (!mtrr_need_cleanup())
+		return 0;
+
+	/* print original var MTRRs at first, for debugging: */
+	printk(KERN_DEBUG "original variable MTRRs\n");
+	print_out_mtrr_range_state();
 
 	memset(range, 0, sizeof(range));
 	extra_remove_size = 0;
@@ -1309,176 +1418,64 @@ static int __init mtrr_cleanup(unsigned address_bits)
 	       range_sums >> (20 - PAGE_SHIFT));
 
 	if (mtrr_chunk_size && mtrr_gran_size) {
-		int num_reg;
-		char gran_factor, chunk_factor, lose_factor;
-		unsigned long gran_base, chunk_base, lose_base;
-
-		debug_print++;
-		/* convert ranges to var ranges state */
-		num_reg = x86_setup_var_mtrrs(range, nr_range, mtrr_chunk_size,
-					      mtrr_gran_size);
+		i = 0;
+		mtrr_calc_range_state(mtrr_chunk_size, mtrr_gran_size,
+				      extra_remove_base, extra_remove_size, i);
 
-		/* we got new setting in range_state, check it */
-		memset(range_new, 0, sizeof(range_new));
-		nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
-						      extra_remove_base,
-						      extra_remove_size);
-		range_sums_new = sum_ranges(range_new, nr_range_new);
+		mtrr_print_out_one_result(i);
 
-		i = 0;
-		result[i].chunk_sizek = mtrr_chunk_size >> 10;
-		result[i].gran_sizek = mtrr_gran_size >> 10;
-		result[i].num_reg = num_reg;
-		if (range_sums < range_sums_new) {
-			result[i].lose_cover_sizek =
-				(range_sums_new - range_sums) << PSHIFT;
-			result[i].bad = 1;
-		} else
-			result[i].lose_cover_sizek =
-				(range_sums - range_sums_new) << PSHIFT;
-
-		gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
-		chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
-		lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
-		printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
-			 result[i].bad?"*BAD*":" ",
-			 gran_base, gran_factor, chunk_base, chunk_factor);
-		printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
-			 result[i].num_reg, result[i].bad?"-":"",
-			 lose_base, lose_factor);
 		if (!result[i].bad) {
 			set_var_mtrr_all(address_bits);
 			return 1;
 		}
 		printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, "
 		       "will find optimal one\n");
-		debug_print--;
-		memset(result, 0, sizeof(result[0]));
 	}
 
 	i = 0;
 	memset(min_loss_pfn, 0xff, sizeof(min_loss_pfn));
 	memset(result, 0, sizeof(result));
 	for (gran_size = (1ULL<<16); gran_size < (1ULL<<32); gran_size <<= 1) {
-		char gran_factor;
-		unsigned long gran_base;
-
-		if (debug_print)
-			gran_base = to_size_factor(gran_size >> 10, &gran_factor);
 
 		for (chunk_size = gran_size; chunk_size < (1ULL<<32);
 		     chunk_size <<= 1) {
-			int num_reg;
 
-			if (debug_print) {
-				char chunk_factor;
-				unsigned long chunk_base;
-
-				chunk_base = to_size_factor(chunk_size>>10, &chunk_factor),
-				printk(KERN_INFO "\n");
-				printk(KERN_INFO "gran_size: %ld%c   chunk_size: %ld%c \n",
-				       gran_base, gran_factor, chunk_base, chunk_factor);
-			}
 			if (i >= NUM_RESULT)
 				continue;
 
-			/* convert ranges to var ranges state */
-			num_reg = x86_setup_var_mtrrs(range, nr_range,
-							 chunk_size, gran_size);
-
-			/* we got new setting in range_state, check it */
-			memset(range_new, 0, sizeof(range_new));
-			nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
-					 extra_remove_base, extra_remove_size);
-			range_sums_new = sum_ranges(range_new, nr_range_new);
-
-			result[i].chunk_sizek = chunk_size >> 10;
-			result[i].gran_sizek = gran_size >> 10;
-			result[i].num_reg = num_reg;
-			if (range_sums < range_sums_new) {
-				result[i].lose_cover_sizek =
-					(range_sums_new - range_sums) << PSHIFT;
-				result[i].bad = 1;
-			} else
-				result[i].lose_cover_sizek =
-					(range_sums - range_sums_new) << PSHIFT;
-
-			/* double check it */
-			if (!result[i].bad && !result[i].lose_cover_sizek) {
-				if (nr_range_new != nr_range ||
-					memcmp(range, range_new, sizeof(range)))
-						result[i].bad = 1;
+			mtrr_calc_range_state(chunk_size, gran_size,
+				      extra_remove_base, extra_remove_size, i);
+			if (debug_print) {
+				mtrr_print_out_one_result(i);
+				printk(KERN_INFO "\n");
 			}
 
-			if (!result[i].bad && (range_sums - range_sums_new <
-					       min_loss_pfn[num_reg])) {
-				min_loss_pfn[num_reg] =
-					range_sums - range_sums_new;
-			}
 			i++;
 		}
 	}
 
-	/* print out all */
-	for (i = 0; i < NUM_RESULT; i++) {
-		char gran_factor, chunk_factor, lose_factor;
-		unsigned long gran_base, chunk_base, lose_base;
-
-		gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
-		chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
-		lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
-		printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
-			 result[i].bad?"*BAD*":" ",
-			 gran_base, gran_factor, chunk_base, chunk_factor);
-		printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
-			 result[i].num_reg, result[i].bad?"-":"",
-			 lose_base, lose_factor);
-	}
-
 	/* try to find the optimal index */
-	if (nr_mtrr_spare_reg >= num_var_ranges)
-		nr_mtrr_spare_reg = num_var_ranges - 1;
-	num_reg_good = -1;
-	for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) {
-		if (!min_loss_pfn[i])
-			num_reg_good = i;
-	}
-
-	index_good = -1;
-	if (num_reg_good != -1) {
-		for (i = 0; i < NUM_RESULT; i++) {
-			if (!result[i].bad &&
-			    result[i].num_reg == num_reg_good &&
-			    !result[i].lose_cover_sizek) {
-				index_good = i;
-				break;
-			}
-		}
-	}
+	index_good = mtrr_search_optimal_index();
 
 	if (index_good != -1) {
-		char gran_factor, chunk_factor, lose_factor;
-		unsigned long gran_base, chunk_base, lose_base;
-
 		printk(KERN_INFO "Found optimal setting for mtrr clean up\n");
 		i = index_good;
-		gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
-		chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
-		lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
-		printk(KERN_INFO "gran_size: %ld%c \tchunk_size: %ld%c \t",
-			 gran_base, gran_factor, chunk_base, chunk_factor);
-		printk(KERN_CONT "num_reg: %d  \tlose RAM: %ld%c\n",
-			 result[i].num_reg, lose_base, lose_factor);
+		mtrr_print_out_one_result(i);
+
 		/* convert ranges to var ranges state */
 		chunk_size = result[i].chunk_sizek;
 		chunk_size <<= 10;
 		gran_size = result[i].gran_sizek;
 		gran_size <<= 10;
-		debug_print++;
 		x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size);
-		debug_print--;
 		set_var_mtrr_all(address_bits);
+		printk(KERN_DEBUG "New variable MTRRs\n");
+		print_out_mtrr_range_state();
 		return 1;
+	} else {
+		/* print out all */
+		for (i = 0; i < NUM_RESULT; i++)
+			mtrr_print_out_one_result(i);
 	}
 
 	printk(KERN_INFO "mtrr_cleanup: can not find optimal value\n");
@@ -1562,7 +1559,6 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 {
 	unsigned long i, base, size, highest_pfn = 0, def, dummy;
 	mtrr_type type;
-	int nr_range;
 	u64 total_trim_size;
 
 	/* extra one for all 0 */

arch/x86/kernel/cpu/vmware.c

@@ -0,0 +1,112 @@
+/*
+ * VMware Detection code.
+ *
+ * Copyright (C) 2008, VMware, Inc.
+ * Author : Alok N Kataria <akataria@vmware.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+
+#include <linux/dmi.h>
+#include <asm/div64.h>
+#include <asm/vmware.h>
+
+#define CPUID_VMWARE_INFO_LEAF	0x40000000
+#define VMWARE_HYPERVISOR_MAGIC	0x564D5868
+#define VMWARE_HYPERVISOR_PORT	0x5658
+
+#define VMWARE_PORT_CMD_GETVERSION	10
+#define VMWARE_PORT_CMD_GETHZ		45
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)				\
+	__asm__("inl (%%dx)" :						\
+			"=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :	\
+			"0"(VMWARE_HYPERVISOR_MAGIC),			\
+			"1"(VMWARE_PORT_CMD_##cmd),			\
+			"2"(VMWARE_HYPERVISOR_PORT), "3"(UINT_MAX) :	\
+			"memory");
+
+static inline int __vmware_platform(void)
+{
+	uint32_t eax, ebx, ecx, edx;
+	VMWARE_PORT(GETVERSION, eax, ebx, ecx, edx);
+	return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC;
+}
+
+static unsigned long __vmware_get_tsc_khz(void)
+{
+        uint64_t tsc_hz;
+        uint32_t eax, ebx, ecx, edx;
+
+        VMWARE_PORT(GETHZ, eax, ebx, ecx, edx);
+
+        if (ebx == UINT_MAX)
+                return 0;
+        tsc_hz = eax | (((uint64_t)ebx) << 32);
+        do_div(tsc_hz, 1000);
+        BUG_ON(tsc_hz >> 32);
+        return tsc_hz;
+}
+
+/*
+ * While checking the dmi string infomation, just checking the product
+ * serial key should be enough, as this will always have a VMware
+ * specific string when running under VMware hypervisor.
+ */
+int vmware_platform(void)
+{
+	if (cpu_has_hypervisor) {
+		unsigned int eax, ebx, ecx, edx;
+		char hyper_vendor_id[13];
+
+		cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &ebx, &ecx, &edx);
+		memcpy(hyper_vendor_id + 0, &ebx, 4);
+		memcpy(hyper_vendor_id + 4, &ecx, 4);
+		memcpy(hyper_vendor_id + 8, &edx, 4);
+		hyper_vendor_id[12] = '\0';
+		if (!strcmp(hyper_vendor_id, "VMwareVMware"))
+			return 1;
+	} else if (dmi_available && dmi_name_in_serial("VMware") &&
+		   __vmware_platform())
+		return 1;
+
+	return 0;
+}
+
+unsigned long vmware_get_tsc_khz(void)
+{
+	BUG_ON(!vmware_platform());
+	return __vmware_get_tsc_khz();
+}
+
+/*
+ * VMware hypervisor takes care of exporting a reliable TSC to the guest.
+ * Still, due to timing difference when running on virtual cpus, the TSC can
+ * be marked as unstable in some cases. For example, the TSC sync check at
+ * bootup can fail due to a marginal offset between vcpus' TSCs (though the
+ * TSCs do not drift from each other).  Also, the ACPI PM timer clocksource
+ * is not suitable as a watchdog when running on a hypervisor because the
+ * kernel may miss a wrap of the counter if the vcpu is descheduled for a
+ * long time. To skip these checks at runtime we set these capability bits,
+ * so that the kernel could just trust the hypervisor with providing a
+ * reliable virtual TSC that is suitable for timekeeping.
+ */
+void __cpuinit vmware_set_feature_bits(struct cpuinfo_x86 *c)
+{
+	set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+	set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE);
+}

arch/x86/kernel/crash.c

@@ -29,34 +29,17 @@
 
 #include <mach_ipi.h>
 
-/* This keeps a track of which one is crashing cpu. */
-static int crashing_cpu;
 
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
-static atomic_t waiting_for_crash_ipi;
 
-static int crash_nmi_callback(struct notifier_block *self,
-			unsigned long val, void *data)
+static void kdump_nmi_callback(int cpu, struct die_args *args)
 {
 	struct pt_regs *regs;
 #ifdef CONFIG_X86_32
 	struct pt_regs fixed_regs;
 #endif
-	int cpu;
 
-	if (val != DIE_NMI_IPI)
-		return NOTIFY_OK;
-
-	regs = ((struct die_args *)data)->regs;
-	cpu = raw_smp_processor_id();
-
-	/* Don't do anything if this handler is invoked on crashing cpu.
-	 * Otherwise, system will completely hang. Crashing cpu can get
-	 * an NMI if system was initially booted with nmi_watchdog parameter.
-	 */
-	if (cpu == crashing_cpu)
-		return NOTIFY_STOP;
-	local_irq_disable();
+	regs = args->regs;
 
 #ifdef CONFIG_X86_32
 	if (!user_mode_vm(regs)) {
@@ -65,54 +48,19 @@ static int crash_nmi_callback(struct notifier_block *self,
 	}
 #endif
 	crash_save_cpu(regs, cpu);
-	disable_local_APIC();
-	atomic_dec(&waiting_for_crash_ipi);
-	/* Assume hlt works */
-	halt();
-	for (;;)
-		cpu_relax();
-
-	return 1;
-}
 
-static void smp_send_nmi_allbutself(void)
-{
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(safe_smp_processor_id(), mask);
-	if (!cpus_empty(mask))
-		send_IPI_mask(mask, NMI_VECTOR);
+	disable_local_APIC();
 }
 
-static struct notifier_block crash_nmi_nb = {
-	.notifier_call = crash_nmi_callback,
-};
-
-static void nmi_shootdown_cpus(void)
+static void kdump_nmi_shootdown_cpus(void)
 {
-	unsigned long msecs;
-
-	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
-	/* Would it be better to replace the trap vector here? */
-	if (register_die_notifier(&crash_nmi_nb))
-		return;		/* return what? */
-	/* Ensure the new callback function is set before sending
-	 * out the NMI
-	 */
-	wmb();
+	nmi_shootdown_cpus(kdump_nmi_callback);
 
-	smp_send_nmi_allbutself();
-
-	msecs = 1000; /* Wait at most a second for the other cpus to stop */
-	while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
-		mdelay(1);
-		msecs--;
-	}
-
-	/* Leave the nmi callback set */
 	disable_local_APIC();
 }
+
 #else
-static void nmi_shootdown_cpus(void)
+static void kdump_nmi_shootdown_cpus(void)
 {
 	/* There are no cpus to shootdown */
 }
@@ -131,9 +79,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 	/* The kernel is broken so disable interrupts */
 	local_irq_disable();
 
-	/* Make a note of crashing cpu. Will be used in NMI callback.*/
-	crashing_cpu = safe_smp_processor_id();
-	nmi_shootdown_cpus();
+	kdump_nmi_shootdown_cpus();
 	lapic_shutdown();
 #if defined(CONFIG_X86_IO_APIC)
 	disable_IO_APIC();

arch/x86/kernel/ds.c

@@ -847,17 +847,16 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
 	switch (c->x86) {
 	case 0x6:
 		switch (c->x86_model) {
+		case 0 ... 0xC:
+			/* sorry, don't know about them */
+			break;
 		case 0xD:
 		case 0xE: /* Pentium M */
 			ds_configure(&ds_cfg_var);
 			break;
-		case 0xF: /* Core2 */
-		case 0x1C: /* Atom */
+		default: /* Core2, Atom, ... */
 			ds_configure(&ds_cfg_64);
 			break;
-		default:
-			/* sorry, don't know about them */
-			break;
 		}
 		break;
 	case 0xF:

arch/x86/kernel/dumpstack.c

@@ -0,0 +1,319 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ */
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/uaccess.h>
+#include <linux/utsname.h>
+#include <linux/hardirq.h>
+#include <linux/kdebug.h>
+#include <linux/module.h>
+#include <linux/ptrace.h>
+#include <linux/kexec.h>
+#include <linux/bug.h>
+#include <linux/nmi.h>
+#include <linux/sysfs.h>
+
+#include <asm/stacktrace.h>
+
+#include "dumpstack.h"
+
+int panic_on_unrecovered_nmi;
+unsigned int code_bytes = 64;
+int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
+static int die_counter;
+
+void printk_address(unsigned long address, int reliable)
+{
+	printk(" [<%p>] %s%pS\n", (void *) address,
+			reliable ? "" : "? ", (void *) address);
+}
+
+/*
+ * x86-64 can have up to three kernel stacks:
+ * process stack
+ * interrupt stack
+ * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
+ */
+
+static inline int valid_stack_ptr(struct thread_info *tinfo,
+			void *p, unsigned int size, void *end)
+{
+	void *t = tinfo;
+	if (end) {
+		if (p < end && p >= (end-THREAD_SIZE))
+			return 1;
+		else
+			return 0;
+	}
+	return p > t && p < t + THREAD_SIZE - size;
+}
+
+unsigned long
+print_context_stack(struct thread_info *tinfo,
+		unsigned long *stack, unsigned long bp,
+		const struct stacktrace_ops *ops, void *data,
+		unsigned long *end)
+{
+	struct stack_frame *frame = (struct stack_frame *)bp;
+
+	while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
+		unsigned long addr;
+
+		addr = *stack;
+		if (__kernel_text_address(addr)) {
+			if ((unsigned long) stack == bp + sizeof(long)) {
+				ops->address(data, addr, 1);
+				frame = frame->next_frame;
+				bp = (unsigned long) frame;
+			} else {
+				ops->address(data, addr, bp == 0);
+			}
+		}
+		stack++;
+	}
+	return bp;
+}
+
+
+static void
+print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
+{
+	printk(data);
+	print_symbol(msg, symbol);
+	printk("\n");
+}
+
+static void print_trace_warning(void *data, char *msg)
+{
+	printk("%s%s\n", (char *)data, msg);
+}
+
+static int print_trace_stack(void *data, char *name)
+{
+	printk("%s <%s> ", (char *)data, name);
+	return 0;
+}
+
+/*
+ * Print one address/symbol entries per line.
+ */
+static void print_trace_address(void *data, unsigned long addr, int reliable)
+{
+	touch_nmi_watchdog();
+	printk(data);
+	printk_address(addr, reliable);
+}
+
+static const struct stacktrace_ops print_trace_ops = {
+	.warning = print_trace_warning,
+	.warning_symbol = print_trace_warning_symbol,
+	.stack = print_trace_stack,
+	.address = print_trace_address,
+};
+
+void
+show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *stack, unsigned long bp, char *log_lvl)
+{
+	printk("%sCall Trace:\n", log_lvl);
+	dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
+}
+
+void show_trace(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *stack, unsigned long bp)
+{
+	show_trace_log_lvl(task, regs, stack, bp, "");
+}
+
+void show_stack(struct task_struct *task, unsigned long *sp)
+{
+	show_stack_log_lvl(task, NULL, sp, 0, "");
+}
+
+/*
+ * The architecture-independent dump_stack generator
+ */
+void dump_stack(void)
+{
+	unsigned long bp = 0;
+	unsigned long stack;
+
+#ifdef CONFIG_FRAME_POINTER
+	if (!bp)
+		get_bp(bp);
+#endif
+
+	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
+		current->pid, current->comm, print_tainted(),
+		init_utsname()->release,
+		(int)strcspn(init_utsname()->version, " "),
+		init_utsname()->version);
+	show_trace(NULL, NULL, &stack, bp);
+}
+EXPORT_SYMBOL(dump_stack);
+
+static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED;
+static int die_owner = -1;
+static unsigned int die_nest_count;
+
+unsigned __kprobes long oops_begin(void)
+{
+	int cpu;
+	unsigned long flags;
+
+	oops_enter();
+
+	/* racy, but better than risking deadlock. */
+	raw_local_irq_save(flags);
+	cpu = smp_processor_id();
+	if (!__raw_spin_trylock(&die_lock)) {
+		if (cpu == die_owner)
+			/* nested oops. should stop eventually */;
+		else
+			__raw_spin_lock(&die_lock);
+	}
+	die_nest_count++;
+	die_owner = cpu;
+	console_verbose();
+	bust_spinlocks(1);
+	return flags;
+}
+
+void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
+{
+	if (regs && kexec_should_crash(current))
+		crash_kexec(regs);
+
+	bust_spinlocks(0);
+	die_owner = -1;
+	add_taint(TAINT_DIE);
+	die_nest_count--;
+	if (!die_nest_count)
+		/* Nest count reaches zero, release the lock. */
+		__raw_spin_unlock(&die_lock);
+	raw_local_irq_restore(flags);
+	oops_exit();
+
+	if (!signr)
+		return;
+	if (in_interrupt())
+		panic("Fatal exception in interrupt");
+	if (panic_on_oops)
+		panic("Fatal exception");
+	do_exit(signr);
+}
+
+int __kprobes __die(const char *str, struct pt_regs *regs, long err)
+{
+#ifdef CONFIG_X86_32
+	unsigned short ss;
+	unsigned long sp;
+#endif
+	printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
+#ifdef CONFIG_PREEMPT
+	printk("PREEMPT ");
+#endif
+#ifdef CONFIG_SMP
+	printk("SMP ");
+#endif
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	printk("DEBUG_PAGEALLOC");
+#endif
+	printk("\n");
+	sysfs_printk_last_file();
+	if (notify_die(DIE_OOPS, str, regs, err,
+			current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
+		return 1;
+
+	show_registers(regs);
+#ifdef CONFIG_X86_32
+	sp = (unsigned long) (&regs->sp);
+	savesegment(ss, ss);
+	if (user_mode(regs)) {
+		sp = regs->sp;
+		ss = regs->ss & 0xffff;
+	}
+	printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
+	print_symbol("%s", regs->ip);
+	printk(" SS:ESP %04x:%08lx\n", ss, sp);
+#else
+	/* Executive summary in case the oops scrolled away */
+	printk(KERN_ALERT "RIP ");
+	printk_address(regs->ip, 1);
+	printk(" RSP <%016lx>\n", regs->sp);
+#endif
+	return 0;
+}
+
+/*
+ * This is gone through when something in the kernel has done something bad
+ * and is about to be terminated:
+ */
+void die(const char *str, struct pt_regs *regs, long err)
+{
+	unsigned long flags = oops_begin();
+	int sig = SIGSEGV;
+
+	if (!user_mode_vm(regs))
+		report_bug(regs->ip, regs);
+
+	if (__die(str, regs, err))
+		sig = 0;
+	oops_end(flags, regs, sig);
+}
+
+void notrace __kprobes
+die_nmi(char *str, struct pt_regs *regs, int do_panic)
+{
+	unsigned long flags;
+
+	if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
+		return;
+
+	/*
+	 * We are in trouble anyway, lets at least try
+	 * to get a message out.
+	 */
+	flags = oops_begin();
+	printk(KERN_EMERG "%s", str);
+	printk(" on CPU%d, ip %08lx, registers:\n",
+		smp_processor_id(), regs->ip);
+	show_registers(regs);
+	oops_end(flags, regs, 0);
+	if (do_panic || panic_on_oops)
+		panic("Non maskable interrupt");
+	nmi_exit();
+	local_irq_enable();
+	do_exit(SIGBUS);
+}
+
+static int __init oops_setup(char *s)
+{
+	if (!s)
+		return -EINVAL;
+	if (!strcmp(s, "panic"))
+		panic_on_oops = 1;
+	return 0;
+}
+early_param("oops", oops_setup);
+
+static int __init kstack_setup(char *s)
+{
+	if (!s)
+		return -EINVAL;
+	kstack_depth_to_print = simple_strtoul(s, NULL, 0);
+	return 0;
+}
+early_param("kstack", kstack_setup);
+
+static int __init code_bytes_setup(char *s)
+{
+	code_bytes = simple_strtoul(s, NULL, 0);
+	if (code_bytes > 8192)
+		code_bytes = 8192;
+
+	return 1;
+}
+__setup("code_bytes=", code_bytes_setup);

arch/x86/kernel/dumpstack.h

@@ -0,0 +1,39 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ */
+
+#ifndef DUMPSTACK_H
+#define DUMPSTACK_H
+
+#ifdef CONFIG_X86_32
+#define STACKSLOTS_PER_LINE 8
+#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
+#else
+#define STACKSLOTS_PER_LINE 4
+#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
+#endif
+
+extern unsigned long
+print_context_stack(struct thread_info *tinfo,
+		unsigned long *stack, unsigned long bp,
+		const struct stacktrace_ops *ops, void *data,
+		unsigned long *end);
+
+extern void
+show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *stack, unsigned long bp, char *log_lvl);
+
+extern void
+show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *sp, unsigned long bp, char *log_lvl);
+
+extern unsigned int code_bytes;
+extern int kstack_depth_to_print;
+
+/* The form of the top of the frame on the stack */
+struct stack_frame {
+	struct stack_frame *next_frame;
+	unsigned long return_address;
+};
+#endif

arch/x86/kernel/dumpstack_32.c

@@ -17,64 +17,7 @@
 
 #include <asm/stacktrace.h>
 
-#define STACKSLOTS_PER_LINE 8
-#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
-
-int panic_on_unrecovered_nmi;
-int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
-static unsigned int code_bytes = 64;
-static int die_counter;
-
-void printk_address(unsigned long address, int reliable)
-{
-	printk(" [<%p>] %s%pS\n", (void *) address,
-			reliable ? "" : "? ", (void *) address);
-}
-
-static inline int valid_stack_ptr(struct thread_info *tinfo,
-			void *p, unsigned int size, void *end)
-{
-	void *t = tinfo;
-	if (end) {
-		if (p < end && p >= (end-THREAD_SIZE))
-			return 1;
-		else
-			return 0;
-	}
-	return p > t && p < t + THREAD_SIZE - size;
-}
-
-/* The form of the top of the frame on the stack */
-struct stack_frame {
-	struct stack_frame *next_frame;
-	unsigned long return_address;
-};
-
-static inline unsigned long
-print_context_stack(struct thread_info *tinfo,
-		unsigned long *stack, unsigned long bp,
-		const struct stacktrace_ops *ops, void *data,
-		unsigned long *end)
-{
-	struct stack_frame *frame = (struct stack_frame *)bp;
-
-	while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
-		unsigned long addr;
-
-		addr = *stack;
-		if (__kernel_text_address(addr)) {
-			if ((unsigned long) stack == bp + sizeof(long)) {
-				ops->address(data, addr, 1);
-				frame = frame->next_frame;
-				bp = (unsigned long) frame;
-			} else {
-				ops->address(data, addr, bp == 0);
-			}
-		}
-		stack++;
-	}
-	return bp;
-}
+#include "dumpstack.h"
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
@@ -119,57 +62,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 }
 EXPORT_SYMBOL(dump_trace);
 
-static void
-print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
-	printk(data);
-	print_symbol(msg, symbol);
-	printk("\n");
-}
-
-static void print_trace_warning(void *data, char *msg)
-{
-	printk("%s%s\n", (char *)data, msg);
-}
-
-static int print_trace_stack(void *data, char *name)
-{
-	printk("%s <%s> ", (char *)data, name);
-	return 0;
-}
-
-/*
- * Print one address/symbol entries per line.
- */
-static void print_trace_address(void *data, unsigned long addr, int reliable)
-{
-	touch_nmi_watchdog();
-	printk(data);
-	printk_address(addr, reliable);
-}
-
-static const struct stacktrace_ops print_trace_ops = {
-	.warning = print_trace_warning,
-	.warning_symbol = print_trace_warning_symbol,
-	.stack = print_trace_stack,
-	.address = print_trace_address,
-};
-
-static void
-show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp, char *log_lvl)
-{
-	printk("%sCall Trace:\n", log_lvl);
-	dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
-}
-
-void show_trace(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp)
-{
-	show_trace_log_lvl(task, regs, stack, bp, "");
-}
-
-static void
+void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *sp, unsigned long bp, char *log_lvl)
 {
@@ -196,33 +89,6 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
 }
 
-void show_stack(struct task_struct *task, unsigned long *sp)
-{
-	show_stack_log_lvl(task, NULL, sp, 0, "");
-}
-
-/*
- * The architecture-independent dump_stack generator
- */
-void dump_stack(void)
-{
-	unsigned long bp = 0;
-	unsigned long stack;
-
-#ifdef CONFIG_FRAME_POINTER
-	if (!bp)
-		get_bp(bp);
-#endif
-
-	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
-		current->pid, current->comm, print_tainted(),
-		init_utsname()->release,
-		(int)strcspn(init_utsname()->version, " "),
-		init_utsname()->version);
-	show_trace(NULL, NULL, &stack, bp);
-}
-
-EXPORT_SYMBOL(dump_stack);
 
 void show_registers(struct pt_regs *regs)
 {
@@ -283,167 +149,3 @@ int is_valid_bugaddr(unsigned long ip)
 	return ud2 == 0x0b0f;
 }
 
-static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED;
-static int die_owner = -1;
-static unsigned int die_nest_count;
-
-unsigned __kprobes long oops_begin(void)
-{
-	unsigned long flags;
-
-	oops_enter();
-
-	if (die_owner != raw_smp_processor_id()) {
-		console_verbose();
-		raw_local_irq_save(flags);
-		__raw_spin_lock(&die_lock);
-		die_owner = smp_processor_id();
-		die_nest_count = 0;
-		bust_spinlocks(1);
-	} else {
-		raw_local_irq_save(flags);
-	}
-	die_nest_count++;
-	return flags;
-}
-
-void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
-{
-	bust_spinlocks(0);
-	die_owner = -1;
-	add_taint(TAINT_DIE);
-	__raw_spin_unlock(&die_lock);
-	raw_local_irq_restore(flags);
-
-	if (!regs)
-		return;
-
-	if (kexec_should_crash(current))
-		crash_kexec(regs);
-	if (in_interrupt())
-		panic("Fatal exception in interrupt");
-	if (panic_on_oops)
-		panic("Fatal exception");
-	oops_exit();
-	do_exit(signr);
-}
-
-int __kprobes __die(const char *str, struct pt_regs *regs, long err)
-{
-	unsigned short ss;
-	unsigned long sp;
-
-	printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
-#ifdef CONFIG_PREEMPT
-	printk("PREEMPT ");
-#endif
-#ifdef CONFIG_SMP
-	printk("SMP ");
-#endif
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	printk("DEBUG_PAGEALLOC");
-#endif
-	printk("\n");
-	sysfs_printk_last_file();
-	if (notify_die(DIE_OOPS, str, regs, err,
-			current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
-		return 1;
-
-	show_registers(regs);
-	/* Executive summary in case the oops scrolled away */
-	sp = (unsigned long) (&regs->sp);
-	savesegment(ss, ss);
-	if (user_mode(regs)) {
-		sp = regs->sp;
-		ss = regs->ss & 0xffff;
-	}
-	printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
-	print_symbol("%s", regs->ip);
-	printk(" SS:ESP %04x:%08lx\n", ss, sp);
-	return 0;
-}
-
-/*
- * This is gone through when something in the kernel has done something bad
- * and is about to be terminated:
- */
-void die(const char *str, struct pt_regs *regs, long err)
-{
-	unsigned long flags = oops_begin();
-
-	if (die_nest_count < 3) {
-		report_bug(regs->ip, regs);
-
-		if (__die(str, regs, err))
-			regs = NULL;
-	} else {
-		printk(KERN_EMERG "Recursive die() failure, output suppressed\n");
-	}
-
-	oops_end(flags, regs, SIGSEGV);
-}
-
-static DEFINE_SPINLOCK(nmi_print_lock);
-
-void notrace __kprobes
-die_nmi(char *str, struct pt_regs *regs, int do_panic)
-{
-	if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
-		return;
-
-	spin_lock(&nmi_print_lock);
-	/*
-	* We are in trouble anyway, lets at least try
-	* to get a message out:
-	*/
-	bust_spinlocks(1);
-	printk(KERN_EMERG "%s", str);
-	printk(" on CPU%d, ip %08lx, registers:\n",
-		smp_processor_id(), regs->ip);
-	show_registers(regs);
-	if (do_panic)
-		panic("Non maskable interrupt");
-	console_silent();
-	spin_unlock(&nmi_print_lock);
-
-	/*
-	 * If we are in kernel we are probably nested up pretty bad
-	 * and might aswell get out now while we still can:
-	 */
-	if (!user_mode_vm(regs)) {
-		current->thread.trap_no = 2;
-		crash_kexec(regs);
-	}
-
-	bust_spinlocks(0);
-	do_exit(SIGSEGV);
-}
-
-static int __init oops_setup(char *s)
-{
-	if (!s)
-		return -EINVAL;
-	if (!strcmp(s, "panic"))
-		panic_on_oops = 1;
-	return 0;
-}
-early_param("oops", oops_setup);
-
-static int __init kstack_setup(char *s)
-{
-	if (!s)
-		return -EINVAL;
-	kstack_depth_to_print = simple_strtoul(s, NULL, 0);
-	return 0;
-}
-early_param("kstack", kstack_setup);
-
-static int __init code_bytes_setup(char *s)
-{
-	code_bytes = simple_strtoul(s, NULL, 0);
-	if (code_bytes > 8192)
-		code_bytes = 8192;
-
-	return 1;
-}
-__setup("code_bytes=", code_bytes_setup);

arch/x86/kernel/dumpstack_64.c

@@ -17,19 +17,7 @@
 
 #include <asm/stacktrace.h>
 
-#define STACKSLOTS_PER_LINE 4
-#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
-
-int panic_on_unrecovered_nmi;
-int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
-static unsigned int code_bytes = 64;
-static int die_counter;
-
-void printk_address(unsigned long address, int reliable)
-{
-	printk(" [<%p>] %s%pS\n", (void *) address,
-			reliable ? "" : "? ", (void *) address);
-}
+#include "dumpstack.h"
 
 static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
 					unsigned *usedp, char **idp)
@@ -113,51 +101,6 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
  * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
  */
 
-static inline int valid_stack_ptr(struct thread_info *tinfo,
-			void *p, unsigned int size, void *end)
-{
-	void *t = tinfo;
-	if (end) {
-		if (p < end && p >= (end-THREAD_SIZE))
-			return 1;
-		else
-			return 0;
-	}
-	return p > t && p < t + THREAD_SIZE - size;
-}
-
-/* The form of the top of the frame on the stack */
-struct stack_frame {
-	struct stack_frame *next_frame;
-	unsigned long return_address;
-};
-
-static inline unsigned long
-print_context_stack(struct thread_info *tinfo,
-		unsigned long *stack, unsigned long bp,
-		const struct stacktrace_ops *ops, void *data,
-		unsigned long *end)
-{
-	struct stack_frame *frame = (struct stack_frame *)bp;
-
-	while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
-		unsigned long addr;
-
-		addr = *stack;
-		if (__kernel_text_address(addr)) {
-			if ((unsigned long) stack == bp + sizeof(long)) {
-				ops->address(data, addr, 1);
-				frame = frame->next_frame;
-				bp = (unsigned long) frame;
-			} else {
-				ops->address(data, addr, bp == 0);
-			}
-		}
-		stack++;
-	}
-	return bp;
-}
-
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data)
@@ -248,57 +191,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 }
 EXPORT_SYMBOL(dump_trace);
 
-static void
-print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
-	printk(data);
-	print_symbol(msg, symbol);
-	printk("\n");
-}
-
-static void print_trace_warning(void *data, char *msg)
-{
-	printk("%s%s\n", (char *)data, msg);
-}
-
-static int print_trace_stack(void *data, char *name)
-{
-	printk("%s <%s> ", (char *)data, name);
-	return 0;
-}
-
-/*
- * Print one address/symbol entries per line.
- */
-static void print_trace_address(void *data, unsigned long addr, int reliable)
-{
-	touch_nmi_watchdog();
-	printk(data);
-	printk_address(addr, reliable);
-}
-
-static const struct stacktrace_ops print_trace_ops = {
-	.warning = print_trace_warning,
-	.warning_symbol = print_trace_warning_symbol,
-	.stack = print_trace_stack,
-	.address = print_trace_address,
-};
-
-static void
-show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp, char *log_lvl)
-{
-	printk("%sCall Trace:\n", log_lvl);
-	dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
-}
-
-void show_trace(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp)
-{
-	show_trace_log_lvl(task, regs, stack, bp, "");
-}
-
-static void
+void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *sp, unsigned long bp, char *log_lvl)
 {
@@ -342,33 +235,6 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
 }
 
-void show_stack(struct task_struct *task, unsigned long *sp)
-{
-	show_stack_log_lvl(task, NULL, sp, 0, "");
-}
-
-/*
- * The architecture-independent dump_stack generator
- */
-void dump_stack(void)
-{
-	unsigned long bp = 0;
-	unsigned long stack;
-
-#ifdef CONFIG_FRAME_POINTER
-	if (!bp)
-		get_bp(bp);
-#endif
-
-	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
-		current->pid, current->comm, print_tainted(),
-		init_utsname()->release,
-		(int)strcspn(init_utsname()->version, " "),
-		init_utsname()->version);
-	show_trace(NULL, NULL, &stack, bp);
-}
-EXPORT_SYMBOL(dump_stack);
-
 void show_registers(struct pt_regs *regs)
 {
 	int i;
@@ -429,147 +295,3 @@ int is_valid_bugaddr(unsigned long ip)
 	return ud2 == 0x0b0f;
 }
 
-static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED;
-static int die_owner = -1;
-static unsigned int die_nest_count;
-
-unsigned __kprobes long oops_begin(void)
-{
-	int cpu;
-	unsigned long flags;
-
-	oops_enter();
-
-	/* racy, but better than risking deadlock. */
-	raw_local_irq_save(flags);
-	cpu = smp_processor_id();
-	if (!__raw_spin_trylock(&die_lock)) {
-		if (cpu == die_owner)
-			/* nested oops. should stop eventually */;
-		else
-			__raw_spin_lock(&die_lock);
-	}
-	die_nest_count++;
-	die_owner = cpu;
-	console_verbose();
-	bust_spinlocks(1);
-	return flags;
-}
-
-void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
-{
-	die_owner = -1;
-	bust_spinlocks(0);
-	die_nest_count--;
-	if (!die_nest_count)
-		/* Nest count reaches zero, release the lock. */
-		__raw_spin_unlock(&die_lock);
-	raw_local_irq_restore(flags);
-	if (!regs) {
-		oops_exit();
-		return;
-	}
-	if (in_interrupt())
-		panic("Fatal exception in interrupt");
-	if (panic_on_oops)
-		panic("Fatal exception");
-	oops_exit();
-	do_exit(signr);
-}
-
-int __kprobes __die(const char *str, struct pt_regs *regs, long err)
-{
-	printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
-#ifdef CONFIG_PREEMPT
-	printk("PREEMPT ");
-#endif
-#ifdef CONFIG_SMP
-	printk("SMP ");
-#endif
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	printk("DEBUG_PAGEALLOC");
-#endif
-	printk("\n");
-	sysfs_printk_last_file();
-	if (notify_die(DIE_OOPS, str, regs, err,
-			current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
-		return 1;
-
-	show_registers(regs);
-	add_taint(TAINT_DIE);
-	/* Executive summary in case the oops scrolled away */
-	printk(KERN_ALERT "RIP ");
-	printk_address(regs->ip, 1);
-	printk(" RSP <%016lx>\n", regs->sp);
-	if (kexec_should_crash(current))
-		crash_kexec(regs);
-	return 0;
-}
-
-void die(const char *str, struct pt_regs *regs, long err)
-{
-	unsigned long flags = oops_begin();
-
-	if (!user_mode(regs))
-		report_bug(regs->ip, regs);
-
-	if (__die(str, regs, err))
-		regs = NULL;
-	oops_end(flags, regs, SIGSEGV);
-}
-
-notrace __kprobes void
-die_nmi(char *str, struct pt_regs *regs, int do_panic)
-{
-	unsigned long flags;
-
-	if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
-		return;
-
-	flags = oops_begin();
-	/*
-	 * We are in trouble anyway, lets at least try
-	 * to get a message out.
-	 */
-	printk(KERN_EMERG "%s", str);
-	printk(" on CPU%d, ip %08lx, registers:\n",
-		smp_processor_id(), regs->ip);
-	show_registers(regs);
-	if (kexec_should_crash(current))
-		crash_kexec(regs);
-	if (do_panic || panic_on_oops)
-		panic("Non maskable interrupt");
-	oops_end(flags, NULL, SIGBUS);
-	nmi_exit();
-	local_irq_enable();
-	do_exit(SIGBUS);
-}
-
-static int __init oops_setup(char *s)
-{
-	if (!s)
-		return -EINVAL;
-	if (!strcmp(s, "panic"))
-		panic_on_oops = 1;
-	return 0;
-}
-early_param("oops", oops_setup);
-
-static int __init kstack_setup(char *s)
-{
-	if (!s)
-		return -EINVAL;
-	kstack_depth_to_print = simple_strtoul(s, NULL, 0);
-	return 0;
-}
-early_param("kstack", kstack_setup);
-
-static int __init code_bytes_setup(char *s)
-{
-	code_bytes = simple_strtoul(s, NULL, 0);
-	if (code_bytes > 8192)
-		code_bytes = 8192;
-
-	return 1;
-}
-__setup("code_bytes=", code_bytes_setup);

arch/x86/kernel/e820.c

@@ -677,22 +677,6 @@ struct early_res {
 };
 static struct early_res early_res[MAX_EARLY_RES] __initdata = {
 	{ 0, PAGE_SIZE, "BIOS data page" },	/* BIOS data page */
-#if defined(CONFIG_X86_64) && defined(CONFIG_X86_TRAMPOLINE)
-	{ TRAMPOLINE_BASE, TRAMPOLINE_BASE + 2 * PAGE_SIZE, "TRAMPOLINE" },
-#endif
-#if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
-	/*
-	 * But first pinch a few for the stack/trampoline stuff
-	 * FIXME: Don't need the extra page at 4K, but need to fix
-	 * trampoline before removing it. (see the GDT stuff)
-	 */
-	{ PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE" },
-	/*
-	 * Has to be in very low memory so we can execute
-	 * real-mode AP code.
-	 */
-	{ TRAMPOLINE_BASE, TRAMPOLINE_BASE + PAGE_SIZE, "TRAMPOLINE" },
-#endif
 	{}
 };
 

arch/x86/kernel/early_printk.c

@@ -875,49 +875,6 @@ static struct console early_dbgp_console = {
 };
 #endif
 
-/* Console interface to a host file on AMD's SimNow! */
-
-static int simnow_fd;
-
-enum {
-	MAGIC1 = 0xBACCD00A,
-	MAGIC2 = 0xCA110000,
-	XOPEN = 5,
-	XWRITE = 4,
-};
-
-static noinline long simnow(long cmd, long a, long b, long c)
-{
-	long ret;
-
-	asm volatile("cpuid" :
-		     "=a" (ret) :
-		     "b" (a), "c" (b), "d" (c), "0" (MAGIC1), "D" (cmd + MAGIC2));
-	return ret;
-}
-
-static void __init simnow_init(char *str)
-{
-	char *fn = "klog";
-
-	if (*str == '=')
-		fn = ++str;
-	/* error ignored */
-	simnow_fd = simnow(XOPEN, (unsigned long)fn, O_WRONLY|O_APPEND|O_CREAT, 0644);
-}
-
-static void simnow_write(struct console *con, const char *s, unsigned n)
-{
-	simnow(XWRITE, simnow_fd, (unsigned long)s, n);
-}
-
-static struct console simnow_console = {
-	.name =		"simnow",
-	.write =	simnow_write,
-	.flags =	CON_PRINTBUFFER,
-	.index =	-1,
-};
-
 /* Direct interface for emergencies */
 static struct console *early_console = &early_vga_console;
 static int __initdata early_console_initialized;
@@ -960,10 +917,6 @@ static int __init setup_early_printk(char *buf)
 		max_ypos = boot_params.screen_info.orig_video_lines;
 		current_ypos = boot_params.screen_info.orig_y;
 		early_console = &early_vga_console;
-	} else if (!strncmp(buf, "simnow", 6)) {
-		simnow_init(buf + 6);
-		early_console = &simnow_console;
-		keep_early = 1;
 #ifdef CONFIG_EARLY_PRINTK_DBGP
 	} else if (!strncmp(buf, "dbgp", 4)) {
 		if (early_dbgp_init(buf+4) < 0)

arch/x86/kernel/entry_32.S

@@ -1051,6 +1051,7 @@ ENTRY(kernel_thread_helper)
 	push %eax
 	CFI_ADJUST_CFA_OFFSET 4
 	call do_exit
+	ud2			# padding for call trace
 	CFI_ENDPROC
 ENDPROC(kernel_thread_helper)
 

arch/x86/kernel/entry_64.S

@@ -11,15 +11,15 @@
  *
  * NOTE: This code handles signal-recognition, which happens every time
  * after an interrupt and after each system call.
- * 
- * Normal syscalls and interrupts don't save a full stack frame, this is 
+ *
+ * Normal syscalls and interrupts don't save a full stack frame, this is
  * only done for syscall tracing, signals or fork/exec et.al.
- * 
- * A note on terminology:	 
- * - top of stack: Architecture defined interrupt frame from SS to RIP 
- * at the top of the kernel process stack.	
+ *
+ * A note on terminology:
+ * - top of stack: Architecture defined interrupt frame from SS to RIP
+ * at the top of the kernel process stack.
  * - partial stack frame: partially saved registers upto R11.
- * - full stack frame: Like partial stack frame, but all register saved. 
+ * - full stack frame: Like partial stack frame, but all register saved.
  *
  * Some macro usage:
  * - CFI macros are used to generate dwarf2 unwind information for better
@@ -142,7 +142,7 @@ END(mcount)
 
 #ifndef CONFIG_PREEMPT
 #define retint_kernel retint_restore_args
-#endif	
+#endif
 
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_usergs_sysret64)
@@ -161,14 +161,14 @@ ENTRY(native_usergs_sysret64)
 .endm
 
 /*
- * C code is not supposed to know about undefined top of stack. Every time 
- * a C function with an pt_regs argument is called from the SYSCALL based 
+ * C code is not supposed to know about undefined top of stack. Every time
+ * a C function with an pt_regs argument is called from the SYSCALL based
  * fast path FIXUP_TOP_OF_STACK is needed.
  * RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs
  * manipulation.
- */        	
-		
-	/* %rsp:at FRAMEEND */ 
+ */
+
+	/* %rsp:at FRAMEEND */
 	.macro FIXUP_TOP_OF_STACK tmp
 	movq	%gs:pda_oldrsp,\tmp
 	movq  	\tmp,RSP(%rsp)
@@ -244,8 +244,8 @@ ENTRY(native_usergs_sysret64)
 	.endm
 /*
  * A newly forked process directly context switches into this.
- */ 	
-/* rdi:	prev */	
+ */
+/* rdi:	prev */
 ENTRY(ret_from_fork)
 	CFI_DEFAULT_STACK
 	push kernel_eflags(%rip)
@@ -255,8 +255,9 @@ ENTRY(ret_from_fork)
 	call schedule_tail
 	GET_THREAD_INFO(%rcx)
 	testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
+	CFI_REMEMBER_STATE
 	jnz rff_trace
-rff_action:	
+rff_action:
 	RESTORE_REST
 	testl $3,CS-ARGOFFSET(%rsp)	# from kernel_thread?
 	je   int_ret_from_sys_call
@@ -264,10 +265,11 @@ rff_action:
 	jnz  int_ret_from_sys_call
 	RESTORE_TOP_OF_STACK %rdi,ARGOFFSET
 	jmp ret_from_sys_call
+	CFI_RESTORE_STATE
 rff_trace:
 	movq %rsp,%rdi
 	call syscall_trace_leave
-	GET_THREAD_INFO(%rcx)	
+	GET_THREAD_INFO(%rcx)
 	jmp rff_action
 	CFI_ENDPROC
 END(ret_from_fork)
@@ -278,20 +280,20 @@ END(ret_from_fork)
  * SYSCALL does not save anything on the stack and does not change the
  * stack pointer.
  */
-		
+
 /*
- * Register setup:	
+ * Register setup:
  * rax  system call number
  * rdi  arg0
- * rcx  return address for syscall/sysret, C arg3 
+ * rcx  return address for syscall/sysret, C arg3
  * rsi  arg1
- * rdx  arg2	
+ * rdx  arg2
  * r10  arg3 	(--> moved to rcx for C)
  * r8   arg4
  * r9   arg5
  * r11  eflags for syscall/sysret, temporary for C
- * r12-r15,rbp,rbx saved by C code, not touched. 		
- * 
+ * r12-r15,rbp,rbx saved by C code, not touched.
+ *
  * Interrupts are off on entry.
  * Only called from user space.
  *
@@ -301,7 +303,7 @@ END(ret_from_fork)
  * When user can change the frames always force IRET. That is because
  * it deals with uncanonical addresses better. SYSRET has trouble
  * with them due to bugs in both AMD and Intel CPUs.
- */ 			 		
+ */
 
 ENTRY(system_call)
 	CFI_STARTPROC	simple
@@ -317,7 +319,7 @@ ENTRY(system_call)
 	 */
 ENTRY(system_call_after_swapgs)
 
-	movq	%rsp,%gs:pda_oldrsp 
+	movq	%rsp,%gs:pda_oldrsp
 	movq	%gs:pda_kernelstack,%rsp
 	/*
 	 * No need to follow this irqs off/on section - it's straight
@@ -325,7 +327,7 @@ ENTRY(system_call_after_swapgs)
 	 */
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_ARGS 8,1
-	movq  %rax,ORIG_RAX-ARGOFFSET(%rsp) 
+	movq  %rax,ORIG_RAX-ARGOFFSET(%rsp)
 	movq  %rcx,RIP-ARGOFFSET(%rsp)
 	CFI_REL_OFFSET rip,RIP-ARGOFFSET
 	GET_THREAD_INFO(%rcx)
@@ -339,19 +341,19 @@ system_call_fastpath:
 	movq %rax,RAX-ARGOFFSET(%rsp)
 /*
  * Syscall return path ending with SYSRET (fast path)
- * Has incomplete stack frame and undefined top of stack. 
- */		
+ * Has incomplete stack frame and undefined top of stack.
+ */
 ret_from_sys_call:
 	movl $_TIF_ALLWORK_MASK,%edi
 	/* edi:	flagmask */
-sysret_check:		
+sysret_check:
 	LOCKDEP_SYS_EXIT
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	movl TI_flags(%rcx),%edx
 	andl %edi,%edx
-	jnz  sysret_careful 
+	jnz  sysret_careful
 	CFI_REMEMBER_STATE
 	/*
 	 * sysretq will re-enable interrupts:
@@ -366,7 +368,7 @@ sysret_check:
 
 	CFI_RESTORE_STATE
 	/* Handle reschedules */
-	/* edx:	work, edi: workmask */	
+	/* edx:	work, edi: workmask */
 sysret_careful:
 	bt $TIF_NEED_RESCHED,%edx
 	jnc sysret_signal
@@ -379,7 +381,7 @@ sysret_careful:
 	CFI_ADJUST_CFA_OFFSET -8
 	jmp sysret_check
 
-	/* Handle a signal */ 
+	/* Handle a signal */
 sysret_signal:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
@@ -398,7 +400,7 @@ sysret_signal:
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	jmp int_with_check
-	
+
 badsys:
 	movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
 	jmp ret_from_sys_call
@@ -437,7 +439,7 @@ sysret_audit:
 #endif	/* CONFIG_AUDITSYSCALL */
 
 	/* Do syscall tracing */
-tracesys:			 
+tracesys:
 #ifdef CONFIG_AUDITSYSCALL
 	testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
 	jz auditsys
@@ -460,8 +462,8 @@ tracesys:
 	call *sys_call_table(,%rax,8)
 	movq %rax,RAX-ARGOFFSET(%rsp)
 	/* Use IRET because user could have changed frame */
-		
-/* 
+
+/*
  * Syscall return path ending with IRET.
  * Has correct top of stack, but partial stack frame.
  */
@@ -505,18 +507,18 @@ int_very_careful:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_REST
-	/* Check for syscall exit trace */	
+	/* Check for syscall exit trace */
 	testl $_TIF_WORK_SYSCALL_EXIT,%edx
 	jz int_signal
 	pushq %rdi
 	CFI_ADJUST_CFA_OFFSET 8
-	leaq 8(%rsp),%rdi	# &ptregs -> arg1	
+	leaq 8(%rsp),%rdi	# &ptregs -> arg1
 	call syscall_trace_leave
 	popq %rdi
 	CFI_ADJUST_CFA_OFFSET -8
 	andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
 	jmp int_restore_rest
-	
+
 int_signal:
 	testl $_TIF_DO_NOTIFY_MASK,%edx
 	jz 1f
@@ -531,11 +533,11 @@ int_restore_rest:
 	jmp int_with_check
 	CFI_ENDPROC
 END(system_call)
-		
-/* 
+
+/*
  * Certain special system calls that need to save a complete full stack frame.
- */ 								
-	
+ */
+
 	.macro PTREGSCALL label,func,arg
 	.globl \label
 \label:
@@ -572,7 +574,7 @@ ENTRY(ptregscall_common)
 	ret
 	CFI_ENDPROC
 END(ptregscall_common)
-	
+
 ENTRY(stub_execve)
 	CFI_STARTPROC
 	popq %r11
@@ -588,11 +590,11 @@ ENTRY(stub_execve)
 	jmp int_ret_from_sys_call
 	CFI_ENDPROC
 END(stub_execve)
-	
+
 /*
  * sigreturn is special because it needs to restore all registers on return.
  * This cannot be done with SYSRET, so use the IRET return path instead.
- */                
+ */
 ENTRY(stub_rt_sigreturn)
 	CFI_STARTPROC
 	addq $8, %rsp
@@ -685,12 +687,12 @@ exit_intr:
 	GET_THREAD_INFO(%rcx)
 	testl $3,CS-ARGOFFSET(%rsp)
 	je retint_kernel
-	
+
 	/* Interrupt came from user space */
 	/*
 	 * Has a correct top of stack, but a partial stack frame
 	 * %rcx: thread info. Interrupts off.
-	 */		
+	 */
 retint_with_reschedule:
 	movl $_TIF_WORK_MASK,%edi
 retint_check:
@@ -763,20 +765,20 @@ retint_careful:
 	pushq %rdi
 	CFI_ADJUST_CFA_OFFSET	8
 	call  schedule
-	popq %rdi		
+	popq %rdi
 	CFI_ADJUST_CFA_OFFSET	-8
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	jmp retint_check
-	
+
 retint_signal:
 	testl $_TIF_DO_NOTIFY_MASK,%edx
 	jz    retint_swapgs
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_REST
-	movq $-1,ORIG_RAX(%rsp) 			
+	movq $-1,ORIG_RAX(%rsp)
 	xorl %esi,%esi		# oldset
 	movq %rsp,%rdi		# &pt_regs
 	call do_notify_resume
@@ -798,14 +800,14 @@ ENTRY(retint_kernel)
 	jnc  retint_restore_args
 	call preempt_schedule_irq
 	jmp exit_intr
-#endif	
+#endif
 
 	CFI_ENDPROC
 END(common_interrupt)
-	
+
 /*
  * APIC interrupts.
- */		
+ */
 	.macro apicinterrupt num,func
 	INTR_FRAME
 	pushq $~(\num)
@@ -823,14 +825,14 @@ ENTRY(threshold_interrupt)
 	apicinterrupt THRESHOLD_APIC_VECTOR,mce_threshold_interrupt
 END(threshold_interrupt)
 
-#ifdef CONFIG_SMP	
+#ifdef CONFIG_SMP
 ENTRY(reschedule_interrupt)
 	apicinterrupt RESCHEDULE_VECTOR,smp_reschedule_interrupt
 END(reschedule_interrupt)
 
 	.macro INVALIDATE_ENTRY num
 ENTRY(invalidate_interrupt\num)
-	apicinterrupt INVALIDATE_TLB_VECTOR_START+\num,smp_invalidate_interrupt	
+	apicinterrupt INVALIDATE_TLB_VECTOR_START+\num,smp_invalidate_interrupt
 END(invalidate_interrupt\num)
 	.endm
 
@@ -869,22 +871,22 @@ END(error_interrupt)
 ENTRY(spurious_interrupt)
 	apicinterrupt SPURIOUS_APIC_VECTOR,smp_spurious_interrupt
 END(spurious_interrupt)
-				
+
 /*
  * Exception entry points.
- */ 		
+ */
 	.macro zeroentry sym
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	pushq $0	/* push error code/oldrax */ 
+	pushq $0	/* push error code/oldrax */
 	CFI_ADJUST_CFA_OFFSET 8
-	pushq %rax	/* push real oldrax to the rdi slot */ 
+	pushq %rax	/* push real oldrax to the rdi slot */
 	CFI_ADJUST_CFA_OFFSET 8
 	CFI_REL_OFFSET rax,0
 	leaq  \sym(%rip),%rax
 	jmp error_entry
 	CFI_ENDPROC
-	.endm	
+	.endm
 
 	.macro errorentry sym
 	XCPT_FRAME
@@ -998,13 +1000,13 @@ paranoid_schedule\trace:
 
 /*
  * Exception entry point. This expects an error code/orig_rax on the stack
- * and the exception handler in %rax.	
- */ 		  				
+ * and the exception handler in %rax.
+ */
 KPROBE_ENTRY(error_entry)
 	_frame RDI
 	CFI_REL_OFFSET rax,0
 	/* rdi slot contains rax, oldrax contains error code */
-	cld	
+	cld
 	subq  $14*8,%rsp
 	CFI_ADJUST_CFA_OFFSET	(14*8)
 	movq %rsi,13*8(%rsp)
@@ -1015,7 +1017,7 @@ KPROBE_ENTRY(error_entry)
 	CFI_REL_OFFSET	rdx,RDX
 	movq %rcx,11*8(%rsp)
 	CFI_REL_OFFSET	rcx,RCX
-	movq %rsi,10*8(%rsp)	/* store rax */ 
+	movq %rsi,10*8(%rsp)	/* store rax */
 	CFI_REL_OFFSET	rax,RAX
 	movq %r8, 9*8(%rsp)
 	CFI_REL_OFFSET	r8,R8
@@ -1025,29 +1027,29 @@ KPROBE_ENTRY(error_entry)
 	CFI_REL_OFFSET	r10,R10
 	movq %r11,6*8(%rsp)
 	CFI_REL_OFFSET	r11,R11
-	movq %rbx,5*8(%rsp) 
+	movq %rbx,5*8(%rsp)
 	CFI_REL_OFFSET	rbx,RBX
-	movq %rbp,4*8(%rsp) 
+	movq %rbp,4*8(%rsp)
 	CFI_REL_OFFSET	rbp,RBP
-	movq %r12,3*8(%rsp) 
+	movq %r12,3*8(%rsp)
 	CFI_REL_OFFSET	r12,R12
-	movq %r13,2*8(%rsp) 
+	movq %r13,2*8(%rsp)
 	CFI_REL_OFFSET	r13,R13
-	movq %r14,1*8(%rsp) 
+	movq %r14,1*8(%rsp)
 	CFI_REL_OFFSET	r14,R14
-	movq %r15,(%rsp) 
+	movq %r15,(%rsp)
 	CFI_REL_OFFSET	r15,R15
-	xorl %ebx,%ebx	
+	xorl %ebx,%ebx
 	testl $3,CS(%rsp)
 	je  error_kernelspace
-error_swapgs:	
+error_swapgs:
 	SWAPGS
 error_sti:
 	TRACE_IRQS_OFF
-	movq %rdi,RDI(%rsp) 	
+	movq %rdi,RDI(%rsp)
 	CFI_REL_OFFSET	rdi,RDI
 	movq %rsp,%rdi
-	movq ORIG_RAX(%rsp),%rsi	/* get error code */ 
+	movq ORIG_RAX(%rsp),%rsi	/* get error code */
 	movq $-1,ORIG_RAX(%rsp)
 	call *%rax
 	/* ebx:	no swapgs flag (1: don't need swapgs, 0: need it) */
@@ -1056,7 +1058,7 @@ error_exit:
 	RESTORE_REST
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	GET_THREAD_INFO(%rcx)	
+	GET_THREAD_INFO(%rcx)
 	testl %eax,%eax
 	jne  retint_kernel
 	LOCKDEP_SYS_EXIT_IRQ
@@ -1072,7 +1074,7 @@ error_kernelspace:
        /* There are two places in the kernel that can potentially fault with
           usergs. Handle them here. The exception handlers after
 	   iret run with kernel gs again, so don't set the user space flag.
-	   B stepping K8s sometimes report an truncated RIP for IRET 
+	   B stepping K8s sometimes report an truncated RIP for IRET
 	   exceptions returning to compat mode. Check for these here too. */
 	leaq irq_return(%rip),%rcx
 	cmpq %rcx,RIP(%rsp)
@@ -1084,17 +1086,17 @@ error_kernelspace:
         je   error_swapgs
 	jmp  error_sti
 KPROBE_END(error_entry)
-	
+
        /* Reload gs selector with exception handling */
-       /* edi:  new selector */ 
+       /* edi:  new selector */
 ENTRY(native_load_gs_index)
 	CFI_STARTPROC
 	pushf
 	CFI_ADJUST_CFA_OFFSET 8
 	DISABLE_INTERRUPTS(CLBR_ANY | ~(CLBR_RDI))
         SWAPGS
-gs_change:     
-        movl %edi,%gs   
+gs_change:
+        movl %edi,%gs
 2:	mfence		/* workaround */
 	SWAPGS
         popf
@@ -1102,20 +1104,20 @@ gs_change:
         ret
 	CFI_ENDPROC
 ENDPROC(native_load_gs_index)
-       
+
         .section __ex_table,"a"
         .align 8
         .quad gs_change,bad_gs
         .previous
         .section .fixup,"ax"
 	/* running with kernelgs */
-bad_gs: 
+bad_gs:
 	SWAPGS			/* switch back to user gs */
 	xorl %eax,%eax
         movl %eax,%gs
         jmp  2b
-        .previous       
-	
+        .previous
+
 /*
  * Create a kernel thread.
  *
@@ -1138,7 +1140,7 @@ ENTRY(kernel_thread)
 
 	xorl %r8d,%r8d
 	xorl %r9d,%r9d
-	
+
 	# clone now
 	call do_fork
 	movq %rax,RAX(%rsp)
@@ -1149,14 +1151,14 @@ ENTRY(kernel_thread)
 	 * so internally to the x86_64 port you can rely on kernel_thread()
 	 * not to reschedule the child before returning, this avoids the need
 	 * of hacks for example to fork off the per-CPU idle tasks.
-         * [Hopefully no generic code relies on the reschedule -AK]	
+         * [Hopefully no generic code relies on the reschedule -AK]
 	 */
 	RESTORE_ALL
 	UNFAKE_STACK_FRAME
 	ret
 	CFI_ENDPROC
 ENDPROC(kernel_thread)
-	
+
 child_rip:
 	pushq $0		# fake return address
 	CFI_STARTPROC
@@ -1170,6 +1172,7 @@ child_rip:
 	# exit
 	mov %eax, %edi
 	call do_exit
+	ud2			# padding for call trace
 	CFI_ENDPROC
 ENDPROC(child_rip)
 
@@ -1191,10 +1194,10 @@ ENDPROC(child_rip)
 ENTRY(kernel_execve)
 	CFI_STARTPROC
 	FAKE_STACK_FRAME $0
-	SAVE_ALL	
+	SAVE_ALL
 	movq %rsp,%rcx
 	call sys_execve
-	movq %rax, RAX(%rsp)	
+	movq %rax, RAX(%rsp)
 	RESTORE_REST
 	testq %rax,%rax
 	je int_ret_from_sys_call
@@ -1213,7 +1216,7 @@ ENTRY(coprocessor_error)
 END(coprocessor_error)
 
 ENTRY(simd_coprocessor_error)
-	zeroentry do_simd_coprocessor_error	
+	zeroentry do_simd_coprocessor_error
 END(simd_coprocessor_error)
 
 ENTRY(device_not_available)
@@ -1225,12 +1228,12 @@ KPROBE_ENTRY(debug)
  	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq $0
-	CFI_ADJUST_CFA_OFFSET 8		
+	CFI_ADJUST_CFA_OFFSET 8
 	paranoidentry do_debug, DEBUG_STACK
 	paranoidexit
 KPROBE_END(debug)
 
-	/* runs on exception stack */	
+	/* runs on exception stack */
 KPROBE_ENTRY(nmi)
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
@@ -1264,7 +1267,7 @@ ENTRY(bounds)
 END(bounds)
 
 ENTRY(invalid_op)
-	zeroentry do_invalid_op	
+	zeroentry do_invalid_op
 END(invalid_op)
 
 ENTRY(coprocessor_segment_overrun)
@@ -1319,7 +1322,7 @@ ENTRY(machine_check)
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq $0
-	CFI_ADJUST_CFA_OFFSET 8	
+	CFI_ADJUST_CFA_OFFSET 8
 	paranoidentry do_machine_check
 	jmp paranoid_exit1
 	CFI_ENDPROC

arch/x86/kernel/es7000_32.c

@@ -38,8 +38,11 @@
 #include <asm/io.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
+#include <asm/atomic.h>
 #include <asm/apicdef.h>
 #include <mach_mpparse.h>
+#include <asm/genapic.h>
+#include <asm/setup.h>
 
 /*
  * ES7000 chipsets
@@ -161,6 +164,43 @@ es7000_rename_gsi(int ioapic, int gsi)
 	return gsi;
 }
 
+static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
+{
+	unsigned long vect = 0, psaival = 0;
+
+	if (psai == NULL)
+		return -1;
+
+	vect = ((unsigned long)__pa(eip)/0x1000) << 16;
+	psaival = (0x1000000 | vect | cpu);
+
+	while (*psai & 0x1000000)
+		;
+
+	*psai = psaival;
+
+	return 0;
+}
+
+static void noop_wait_for_deassert(atomic_t *deassert_not_used)
+{
+}
+
+static int __init es7000_update_genapic(void)
+{
+	genapic->wakeup_cpu = wakeup_secondary_cpu_via_mip;
+
+	/* MPENTIUMIII */
+	if (boot_cpu_data.x86 == 6 &&
+	    (boot_cpu_data.x86_model >= 7 || boot_cpu_data.x86_model <= 11)) {
+		es7000_update_genapic_to_cluster();
+		genapic->wait_for_init_deassert = noop_wait_for_deassert;
+		genapic->wakeup_cpu = wakeup_secondary_cpu_via_mip;
+	}
+
+	return 0;
+}
+
 void __init
 setup_unisys(void)
 {
@@ -176,6 +216,8 @@ setup_unisys(void)
 	else
 		es7000_plat = ES7000_CLASSIC;
 	ioapic_renumber_irq = es7000_rename_gsi;
+
+	x86_quirks->update_genapic = es7000_update_genapic;
 }
 
 /*
@@ -317,26 +359,6 @@ es7000_mip_write(struct mip_reg *mip_reg)
 	return status;
 }
 
-int
-es7000_start_cpu(int cpu, unsigned long eip)
-{
-	unsigned long vect = 0, psaival = 0;
-
-	if (psai == NULL)
-		return -1;
-
-	vect = ((unsigned long)__pa(eip)/0x1000) << 16;
-	psaival = (0x1000000 | vect | cpu);
-
-	while (*psai & 0x1000000)
-                ;
-
-	*psai = psaival;
-
-	return 0;
-
-}
-
 void __init
 es7000_sw_apic(void)
 {

arch/x86/kernel/genapic_64.c

@@ -21,6 +21,7 @@
 #include <asm/smp.h>
 #include <asm/ipi.h>
 #include <asm/genapic.h>
+#include <asm/setup.h>
 
 extern struct genapic apic_flat;
 extern struct genapic apic_physflat;
@@ -53,6 +54,9 @@ void __init setup_apic_routing(void)
 			genapic = &apic_physflat;
 		printk(KERN_INFO "Setting APIC routing to %s\n", genapic->name);
 	}
+
+	if (x86_quirks->update_genapic)
+		x86_quirks->update_genapic();
 }
 
 /* Same for both flat and physical. */

arch/x86/kernel/genx2apic_uv_x.c

@@ -10,6 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/threads.h>
+#include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
@@ -17,6 +18,9 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/hardirq.h>
+#include <linux/timer.h>
+#include <linux/proc_fs.h>
+#include <asm/current.h>
 #include <asm/smp.h>
 #include <asm/ipi.h>
 #include <asm/genapic.h>
@@ -355,6 +359,103 @@ static __init void uv_rtc_init(void)
 		sn_rtc_cycles_per_second = ticks_per_sec;
 }
 
+/*
+ * percpu heartbeat timer
+ */
+static void uv_heartbeat(unsigned long ignored)
+{
+	struct timer_list *timer = &uv_hub_info->scir.timer;
+	unsigned char bits = uv_hub_info->scir.state;
+
+	/* flip heartbeat bit */
+	bits ^= SCIR_CPU_HEARTBEAT;
+
+	/* is this cpu idle? */
+	if (idle_cpu(raw_smp_processor_id()))
+		bits &= ~SCIR_CPU_ACTIVITY;
+	else
+		bits |= SCIR_CPU_ACTIVITY;
+
+	/* update system controller interface reg */
+	uv_set_scir_bits(bits);
+
+	/* enable next timer period */
+	mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL);
+}
+
+static void __cpuinit uv_heartbeat_enable(int cpu)
+{
+	if (!uv_cpu_hub_info(cpu)->scir.enabled) {
+		struct timer_list *timer = &uv_cpu_hub_info(cpu)->scir.timer;
+
+		uv_set_cpu_scir_bits(cpu, SCIR_CPU_HEARTBEAT|SCIR_CPU_ACTIVITY);
+		setup_timer(timer, uv_heartbeat, cpu);
+		timer->expires = jiffies + SCIR_CPU_HB_INTERVAL;
+		add_timer_on(timer, cpu);
+		uv_cpu_hub_info(cpu)->scir.enabled = 1;
+	}
+
+	/* check boot cpu */
+	if (!uv_cpu_hub_info(0)->scir.enabled)
+		uv_heartbeat_enable(0);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void __cpuinit uv_heartbeat_disable(int cpu)
+{
+	if (uv_cpu_hub_info(cpu)->scir.enabled) {
+		uv_cpu_hub_info(cpu)->scir.enabled = 0;
+		del_timer(&uv_cpu_hub_info(cpu)->scir.timer);
+	}
+	uv_set_cpu_scir_bits(cpu, 0xff);
+}
+
+/*
+ * cpu hotplug notifier
+ */
+static __cpuinit int uv_scir_cpu_notify(struct notifier_block *self,
+				       unsigned long action, void *hcpu)
+{
+	long cpu = (long)hcpu;
+
+	switch (action) {
+	case CPU_ONLINE:
+		uv_heartbeat_enable(cpu);
+		break;
+	case CPU_DOWN_PREPARE:
+		uv_heartbeat_disable(cpu);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static __init void uv_scir_register_cpu_notifier(void)
+{
+	hotcpu_notifier(uv_scir_cpu_notify, 0);
+}
+
+#else /* !CONFIG_HOTPLUG_CPU */
+
+static __init void uv_scir_register_cpu_notifier(void)
+{
+}
+
+static __init int uv_init_heartbeat(void)
+{
+	int cpu;
+
+	if (is_uv_system())
+		for_each_online_cpu(cpu)
+			uv_heartbeat_enable(cpu);
+	return 0;
+}
+
+late_initcall(uv_init_heartbeat);
+
+#endif /* !CONFIG_HOTPLUG_CPU */
+
 /*
  * Called on each cpu to initialize the per_cpu UV data area.
  * 	ZZZ hotplug not supported yet
@@ -428,7 +529,7 @@ void __init uv_system_init(void)
 
 	uv_bios_init();
 	uv_bios_get_sn_info(0, &uv_type, &sn_partition_id,
-			    &uv_coherency_id, &uv_region_size);
+			    &sn_coherency_id, &sn_region_size);
 	uv_rtc_init();
 
 	for_each_present_cpu(cpu) {
@@ -439,8 +540,7 @@ void __init uv_system_init(void)
 		uv_blade_info[blade].nr_possible_cpus++;
 
 		uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base;
-		uv_cpu_hub_info(cpu)->lowmem_remap_top =
-					lowmem_redir_base + lowmem_redir_size;
+		uv_cpu_hub_info(cpu)->lowmem_remap_top = lowmem_redir_size;
 		uv_cpu_hub_info(cpu)->m_val = m_val;
 		uv_cpu_hub_info(cpu)->n_val = m_val;
 		uv_cpu_hub_info(cpu)->numa_blade_id = blade;
@@ -450,7 +550,8 @@ void __init uv_system_init(void)
 		uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
 		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
 		uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
-		uv_cpu_hub_info(cpu)->coherency_domain_number = uv_coherency_id;
+		uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id;
+		uv_cpu_hub_info(cpu)->scir.offset = SCIR_LOCAL_MMR_BASE + lcpu;
 		uv_node_to_blade[nid] = blade;
 		uv_cpu_to_blade[cpu] = blade;
 		max_pnode = max(pnode, max_pnode);
@@ -467,4 +568,6 @@ void __init uv_system_init(void)
 	map_mmioh_high(max_pnode);
 
 	uv_cpu_init();
+	uv_scir_register_cpu_notifier();
+	proc_mkdir("sgi_uv", NULL);
 }

arch/x86/kernel/head.c

@@ -35,7 +35,6 @@ void __init reserve_ebda_region(void)
 
 	/* start of EBDA area */
 	ebda_addr = get_bios_ebda();
-	printk(KERN_INFO "BIOS EBDA/lowmem at: %08x/%08x\n", ebda_addr, lowmem);
 
 	/* Fixup: bios puts an EBDA in the top 64K segment */
 	/* of conventional memory, but does not adjust lowmem. */

arch/x86/kernel/head32.c

@@ -12,9 +12,12 @@
 #include <asm/sections.h>
 #include <asm/e820.h>
 #include <asm/bios_ebda.h>
+#include <asm/trampoline.h>
 
 void __init i386_start_kernel(void)
 {
+	reserve_trampoline_memory();
+
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD

arch/x86/kernel/head64.c

@@ -24,6 +24,7 @@
 #include <asm/kdebug.h>
 #include <asm/e820.h>
 #include <asm/bios_ebda.h>
+#include <asm/trampoline.h>
 
 /* boot cpu pda */
 static struct x8664_pda _boot_cpu_pda __read_mostly;
@@ -120,6 +121,8 @@ void __init x86_64_start_reservations(char *real_mode_data)
 {
 	copy_bootdata(__va(real_mode_data));
 
+	reserve_trampoline_memory();
+
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD