Merge branch 'for-linus' of git://one.firstfloor.org/home/andi/git/li…

…nux-2.6

* 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6: (225 commits)
  [PATCH] Don't set calgary iommu as default y
  [PATCH] i386/x86-64: New Intel feature flags
  [PATCH] x86: Add a cumulative thermal throttle event counter.
  [PATCH] i386: Make the jiffies compares use the 64bit safe macros.
  [PATCH] x86: Refactor thermal throttle processing
  [PATCH] Add 64bit jiffies compares (for use with get_jiffies_64)
  [PATCH] Fix unwinder warning in traps.c
  [PATCH] x86: Allow disabling early pci scans with pci=noearly or disallowing conf1
  [PATCH] x86: Move direct PCI scanning functions out of line
  [PATCH] i386/x86-64: Make all early PCI scans dependent on CONFIG_PCI
  [PATCH] Don't leak NT bit into next task
  [PATCH] i386/x86-64: Work around gcc bug with noreturn functions in unwinder
  [PATCH] Fix some broken white space in ia32_signal.c
  [PATCH] Initialize argument registers for 32bit signal handlers.
  [PATCH] Remove all traces of signal number conversion
  [PATCH] Don't synchronize time reading on single core AMD systems
  [PATCH] Remove outdated comment in x86-64 mmconfig code
  [PATCH] Use string instructions for Core2 copy/clear
  [PATCH] x86: - restore i8259A eoi status on resume
  [PATCH] i386: Split multi-line printk in oops output.
  ...

Documentation/HOWTO

@@ -358,7 +358,8 @@ Here is a list of some of the different kernel trees available:
   quilt trees:
     - USB, PCI, Driver Core, and I2C, Greg Kroah-Hartman <[email protected]>
 	kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
-
+    - x86-64, partly i386, Andi Kleen <[email protected]>
+        ftp.firstfloor.org:/pub/ak/x86_64/quilt/
 
 Bug Reporting
 -------------

Documentation/filesystems/proc.txt

@@ -1124,11 +1124,15 @@ debugging information is displayed on console.
 NMI switch that most IA32 servers have fires unknown NMI up, for example.
 If a system hangs up, try pressing the NMI switch.
 
-[NOTE]
-   This function and oprofile share a NMI callback. Therefore this function
-   cannot be enabled when oprofile is activated.
-   And NMI watchdog will be disabled when the value in this file is set to
-   non-zero.
+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.
+
+Because the NMI watchdog shares registers with oprofile, by disabling the NMI
+watchdog, oprofile may have more registers to utilize.
 
 
 2.4 /proc/sys/vm - The virtual memory subsystem

Documentation/kbuild/makefiles.txt

@@ -421,6 +421,11 @@ more details, with real examples.
 	The second argument is optional, and if supplied will be used
 	if first argument is not supported.
 
+    as-instr
+	as-instr checks if the assembler reports a specific instruction
+	and then outputs either option1 or option2
+	C escapes are supported in the test instruction
+
     cc-option
 	cc-option is used to check if $(CC) supports a given option, and not
 	supported to use an optional second option.

Documentation/kernel-parameters.txt

@@ -1240,7 +1240,11 @@ running once the system is up.
 				bootloader. This is currently used on
 				IXP2000 systems where the bus has to be
 				configured a certain way for adjunct CPUs.
-
+		noearly		[X86] Don't do any early type 1 scanning.
+				This might help on some broken boards which
+				machine check when some devices' config space
+				is read. But various workarounds are disabled
+				and some IOMMU drivers will not work.
 	pcmv=		[HW,PCMCIA] BadgePAD 4
 
 	pd.		[PARIDE]

Documentation/x86_64/boot-options.txt

@@ -245,6 +245,13 @@ Debugging
 		newfallback: use new unwinder but fall back to old if it gets
 			stuck (default)
 
+  call_trace=[old|both|newfallback|new]
+		old: use old inexact backtracer
+		new: use new exact dwarf2 unwinder
+ 		both: print entries from both
+		newfallback: use new unwinder but fall back to old if it gets
+			stuck (default)
+
 Misc
 
   noreplacement  Don't replace instructions with more appropriate ones

Documentation/x86_64/kernel-stacks

@@ -0,0 +1,99 @@
+Most of the text from Keith Owens, hacked by AK
+
+x86_64 page size (PAGE_SIZE) is 4K.
+
+Like all other architectures, x86_64 has a kernel stack for every
+active thread.  These thread stacks are THREAD_SIZE (2*PAGE_SIZE) big.
+These stacks contain useful data as long as a thread is alive or a
+zombie. While the thread is in user space the kernel stack is empty
+except for the thread_info structure at the bottom.
+
+In addition to the per thread stacks, there are specialized stacks
+associated with each cpu.  These stacks are only used while the kernel
+is in control on that cpu, when a cpu returns to user space the
+specialized stacks contain no useful data.  The main cpu stacks is
+
+* Interrupt stack.  IRQSTACKSIZE
+
+  Used for external hardware interrupts.  If this is the first external
+  hardware interrupt (i.e. not a nested hardware interrupt) then the
+  kernel switches from the current task to the interrupt stack.  Like
+  the split thread and interrupt stacks on i386 (with CONFIG_4KSTACKS),
+  this gives more room for kernel interrupt processing without having
+  to increase the size of every per thread stack.
+
+  The interrupt stack is also used when processing a softirq.
+
+Switching to the kernel interrupt stack is done by software based on a
+per CPU interrupt nest counter. This is needed because x86-64 "IST"
+hardware stacks cannot nest without races.
+
+x86_64 also has a feature which is not available on i386, the ability
+to automatically switch to a new stack for designated events such as
+double fault or NMI, which makes it easier to handle these unusual
+events on x86_64.  This feature is called the Interrupt Stack Table
+(IST).  There can be up to 7 IST entries per cpu. The IST code is an
+index into the Task State Segment (TSS), the IST entries in the TSS
+point to dedicated stacks, each stack can be a different size.
+
+An IST is selected by an non-zero value in the IST field of an
+interrupt-gate descriptor.  When an interrupt occurs and the hardware
+loads such a descriptor, the hardware automatically sets the new stack
+pointer based on the IST value, then invokes the interrupt handler.  If
+software wants to allow nested IST interrupts then the handler must
+adjust the IST values on entry to and exit from the interrupt handler.
+(this is occasionally done, e.g. for debug exceptions)
+
+Events with different IST codes (i.e. with different stacks) can be
+nested.  For example, a debug interrupt can safely be interrupted by an
+NMI.  arch/x86_64/kernel/entry.S::paranoidentry adjusts the stack
+pointers on entry to and exit from all IST events, in theory allowing
+IST events with the same code to be nested.  However in most cases, the
+stack size allocated to an IST assumes no nesting for the same code.
+If that assumption is ever broken then the stacks will become corrupt.
+
+The currently assigned IST stacks are :-
+
+* STACKFAULT_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+
+  Used for interrupt 12 - Stack Fault Exception (#SS).
+
+  This allows to recover from invalid stack segments. Rarely
+  happens.
+
+* DOUBLEFAULT_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+
+  Used for interrupt 8 - Double Fault Exception (#DF).
+
+  Invoked when handling a exception causes another exception. Happens
+  when the kernel is very confused (e.g. kernel stack pointer corrupt)
+  Using a separate stack allows to recover from it well enough in many
+  cases to still output an oops.
+
+* NMI_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+
+  Used for non-maskable interrupts (NMI).
+
+  NMI can be delivered at any time, including when the kernel is in the
+  middle of switching stacks.  Using IST for NMI events avoids making
+  assumptions about the previous state of the kernel stack.
+
+* DEBUG_STACK.  DEBUG_STKSZ
+
+  Used for hardware debug interrupts (interrupt 1) and for software
+  debug interrupts (INT3).
+
+  When debugging a kernel, debug interrupts (both hardware and
+  software) can occur at any time.  Using IST for these interrupts
+  avoids making assumptions about the previous state of the kernel
+  stack.
+
+* MCE_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+
+  Used for interrupt 18 - Machine Check Exception (#MC).
+
+  MCE can be delivered at any time, including when the kernel is in the
+  middle of switching stacks.  Using IST for MCE events avoids making
+  assumptions about the previous state of the kernel stack.
+
+For more details see the Intel IA32 or AMD AMD64 architecture manuals.

arch/i386/Kconfig

@@ -166,7 +166,6 @@ config X86_VISWS
 
 config X86_GENERICARCH
        bool "Generic architecture (Summit, bigsmp, ES7000, default)"
-       depends on SMP
        help
           This option compiles in the Summit, bigsmp, ES7000, default subarchitectures.
 	  It is intended for a generic binary kernel.
@@ -263,7 +262,7 @@ source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors"
-	depends on !SMP && !(X86_VISWS || X86_VOYAGER)
+	depends on !SMP && !(X86_VISWS || X86_VOYAGER || X86_GENERICARCH)
 	help
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -288,12 +287,12 @@ config X86_UP_IOAPIC
 
 config X86_LOCAL_APIC
 	bool
-	depends on X86_UP_APIC || ((X86_VISWS || SMP) && !X86_VOYAGER)
+	depends on X86_UP_APIC || ((X86_VISWS || SMP) && !X86_VOYAGER) || X86_GENERICARCH
 	default y
 
 config X86_IO_APIC
 	bool
-	depends on X86_UP_IOAPIC || (SMP && !(X86_VISWS || X86_VOYAGER))
+	depends on X86_UP_IOAPIC || (SMP && !(X86_VISWS || X86_VOYAGER)) || X86_GENERICARCH
 	default y
 
 config X86_VISWS_APIC
@@ -741,8 +740,7 @@ config SECCOMP
 source kernel/Kconfig.hz
 
 config KEXEC
-	bool "kexec system call (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	bool "kexec system call"
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot
@@ -763,6 +761,13 @@ config CRASH_DUMP
 	depends on HIGHMEM
 	help
 	  Generate crash dump after being started by kexec.
+          This should be normally only set in special crash dump kernels
+	  which are loaded in the main kernel with kexec-tools into
+	  a specially reserved region and then later executed after
+	  a crash by kdump/kexec. The crash dump kernel must be compiled
+          to a memory address not used by the main kernel or BIOS using
+          PHYSICAL_START.
+	  For more details see Documentation/kdump/kdump.txt
 
 config PHYSICAL_START
 	hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP)

arch/i386/Makefile

@@ -46,6 +46,14 @@ cflags-y += -ffreestanding
 # a lot more stack due to the lack of sharing of stacklots:
 CFLAGS				+= $(shell if [ $(call cc-version) -lt 0400 ] ; then echo $(call cc-option,-fno-unit-at-a-time); fi ;)
 
+# do binutils support CFI?
+cflags-y += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
+AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
+
+# is .cfi_signal_frame supported too?
+cflags-y += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
+AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
+
 CFLAGS += $(cflags-y)
 
 # Default subarch .c files

arch/i386/boot/edd.S

@@ -15,42 +15,95 @@
 #include <asm/setup.h>
 
 #if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
+
+# It is assumed that %ds == INITSEG here
+
 	movb	$0, (EDD_MBR_SIG_NR_BUF)
 	movb	$0, (EDDNR)
 
-# Check the command line for two options:
+# Check the command line for options:
 # edd=of  disables EDD completely  (edd=off)
 # edd=sk  skips the MBR test    (edd=skipmbr)
+# edd=on  re-enables EDD (edd=on)
+
 	pushl	%esi
-    	cmpl	$0, %cs:cmd_line_ptr
-	jz	done_cl
+	movw	$edd_mbr_sig_start, %di	# Default to edd=on
+
 	movl	%cs:(cmd_line_ptr), %esi
-# ds:esi has the pointer to the command line now
-	movl	$(COMMAND_LINE_SIZE-7), %ecx
-# loop through kernel command line one byte at a time
-cl_loop:
-	cmpl	$EDD_CL_EQUALS, (%si)
+	andl	%esi, %esi
+	jz	old_cl			# Old boot protocol?
+
+# Convert to a real-mode pointer in fs:si
+	movl	%esi, %eax
+	shrl	$4, %eax
+	movw	%ax, %fs
+	andw	$0xf, %si
+	jmp	have_cl_pointer
+
+# Old-style boot protocol?
+old_cl:
+	push	%ds			# aka INITSEG
+	pop	%fs
+
+	cmpw	$0xa33f, (0x20)
+	jne	done_cl			# No command line at all?
+	movw	(0x22), %si		# Pointer relative to INITSEG
+
+# fs:si has the pointer to the command line now
+have_cl_pointer:
+
+# Loop through kernel command line one byte at a time.  Just in
+# case the loader is buggy and failed to null-terminate the command line
+# terminate if we get close enough to the end of the segment that we
+# cannot fit "edd=XX"...
+cl_atspace:
+	cmpw	$-5, %si		# Watch for segment wraparound
+	jae	done_cl
+	movl	%fs:(%si), %eax
+	andb	%al, %al		# End of line?
+	jz	done_cl
+	cmpl	$EDD_CL_EQUALS, %eax
 	jz	found_edd_equals
-	incl	%esi
-	loop	cl_loop
-	jmp	done_cl
+	cmpb	$0x20, %al		# <= space consider whitespace
+	ja	cl_skipword
+	incw	%si
+	jmp	cl_atspace
+
+cl_skipword:
+	cmpw	$-5, %si		# Watch for segment wraparound
+	jae	done_cl
+	movb	%fs:(%si), %al		# End of string?
+	andb	%al, %al
+	jz	done_cl
+	cmpb	$0x20, %al
+	jbe	cl_atspace
+	incw	%si
+	jmp	cl_skipword
+
 found_edd_equals:
 # only looking at first two characters after equals
-    	addl	$4, %esi
-	cmpw	$EDD_CL_OFF, (%si)	# edd=of
-	jz	do_edd_off
-	cmpw	$EDD_CL_SKIP, (%si)	# edd=sk
-	jz	do_edd_skipmbr
-	jmp	done_cl
+# late overrides early on the command line, so keep going after finding something
+	movw	%fs:4(%si), %ax
+	cmpw	$EDD_CL_OFF, %ax	# edd=of
+	je	do_edd_off
+	cmpw	$EDD_CL_SKIP, %ax	# edd=sk
+	je	do_edd_skipmbr
+	cmpw	$EDD_CL_ON, %ax		# edd=on
+	je	do_edd_on
+	jmp	cl_skipword
 do_edd_skipmbr:
-    	popl	%esi
-	jmp	edd_start
+	movw	$edd_start, %di
+	jmp	cl_skipword
 do_edd_off:
-	popl	%esi
-	jmp	edd_done
+	movw	$edd_done, %di
+	jmp	cl_skipword
+do_edd_on:
+	movw	$edd_mbr_sig_start, %di
+	jmp	cl_skipword
+
 done_cl:
 	popl	%esi
-
+	jmpw	*%di
 
 # Read the first sector of each BIOS disk device and store the 4-byte signature
 edd_mbr_sig_start:

arch/i386/boot/setup.S

@@ -494,12 +494,12 @@ no_voyager:
 	movw	%cs, %ax			# aka SETUPSEG
 	subw	$DELTA_INITSEG, %ax		# aka INITSEG
 	movw	%ax, %ds
-	movw	$0, (0x1ff)			# default is no pointing device
+	movb	$0, (0x1ff)			# default is no pointing device
 	int	$0x11				# int 0x11: equipment list
 	testb	$0x04, %al			# check if mouse installed
 	jz	no_psmouse
 
-	movw	$0xAA, (0x1ff)			# device present
+	movb	$0xAA, (0x1ff)			# device present
 no_psmouse:
 
 #if defined(CONFIG_X86_SPEEDSTEP_SMI) || defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE)