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: (94 commits)
  [PATCH] x86-64: Remove mk_pte_phys()
  [PATCH] i386: Fix broken CONFIG_COMPAT_VDSO on i386
  [PATCH] i386: fix 32-bit ioctls on x64_32
  [PATCH] x86: Unify pcspeaker platform device code between i386/x86-64
  [PATCH] i386: Remove extern declaration from mm/discontig.c, put in header.
  [PATCH] i386: Rename cpu_gdt_descr and remove extern declaration from smpboot.c
  [PATCH] i386: Move mce_disabled to asm/mce.h
  [PATCH] i386: paravirt unhandled fallthrough
  [PATCH] x86_64: Wire up compat epoll_pwait
  [PATCH] x86: Don't require the vDSO for handling a.out signals
  [PATCH] i386: Fix Cyrix MediaGX detection
  [PATCH] i386: Fix warning in cpu initialization
  [PATCH] i386: Fix warning in microcode.c
  [PATCH] x86: Enable NMI watchdog for AMD Family 0x10 CPUs
  [PATCH] x86: Add new CPUID bits for AMD Family 10 CPUs in /proc/cpuinfo
  [PATCH] i386: Remove fastcall in paravirt.[ch]
  [PATCH] x86-64: Fix wrong gcc check in bitops.h
  [PATCH] x86-64: survive having no irq mapping for a vector
  [PATCH] i386: geode configuration fixes
  [PATCH] i386: add option to show more code in oops reports
  ...

Documentation/kernel-parameters.txt

@@ -104,6 +104,9 @@ loader, and have no meaning to the kernel directly.
 Do not modify the syntax of boot loader parameters without extreme
 need or coordination with <Documentation/i386/boot.txt>.
 
+There are also arch-specific kernel-parameters not documented here.
+See for example <Documentation/x86_64/boot-options.txt>.
+
 Note that ALL kernel parameters listed below are CASE SENSITIVE, and that
 a trailing = on the name of any parameter states that that parameter will
 be entered as an environment variable, whereas its absence indicates that
@@ -361,6 +364,11 @@ and is between 256 and 4096 characters. It is defined in the file
 			clocksource is not available, it defaults to PIT.
 			Format: { pit | tsc | cyclone | pmtmr }
 
+	code_bytes	[IA32] How many bytes of object code to print in an
+			oops report.
+			Range: 0 - 8192
+			Default: 64
+
 	disable_8254_timer
 	enable_8254_timer
 			[IA32/X86_64] Disable/Enable interrupt 0 timer routing

Documentation/x86_64/boot-options.txt

@@ -180,40 +180,81 @@ PCI
   pci=lastbus=NUMBER	       Scan upto NUMBER busses, no matter what the mptable says.
   pci=noacpi		Don't use ACPI to set up PCI interrupt routing.
 
-IOMMU
-
- iommu=[size][,noagp][,off][,force][,noforce][,leak][,memaper[=order]][,merge]
-         [,forcesac][,fullflush][,nomerge][,noaperture][,calgary]
-   size  set size of iommu (in bytes)
-   noagp don't initialize the AGP driver and use full aperture.
-   off   don't use the IOMMU
-   leak  turn on simple iommu leak tracing (only when CONFIG_IOMMU_LEAK is on)
-   memaper[=order] allocate an own aperture over RAM with size 32MB^order.
-   noforce don't force IOMMU usage. Default.
-   force  Force IOMMU.
-   merge  Do SG merging. Implies force (experimental)
-   nomerge Don't do SG merging.
-   forcesac For SAC mode for masks <40bits  (experimental)
-   fullflush Flush IOMMU on each allocation (default)
-   nofullflush Don't use IOMMU fullflush
-   allowed  overwrite iommu off workarounds for specific chipsets.
-   soft	 Use software bounce buffering (default for Intel machines)
-   noaperture Don't touch the aperture for AGP.
-   allowdac Allow DMA >4GB
-	    When off all DMA over >4GB is forced through an IOMMU or bounce
-	    buffering.
-   nodac    Forbid DMA >4GB
-   panic    Always panic when IOMMU overflows
-   calgary  Use the Calgary IOMMU if it is available
-
-  swiotlb=pages[,force]
-
-  pages  Prereserve that many 128K pages for the software IO bounce buffering.
-  force  Force all IO through the software TLB.
-
-  calgary=[64k,128k,256k,512k,1M,2M,4M,8M]
-  calgary=[translate_empty_slots]
-  calgary=[disable=<PCI bus number>]
+IOMMU (input/output memory management unit)
+
+ Currently four x86-64 PCI-DMA mapping implementations exist:
+
+   1. <arch/x86_64/kernel/pci-nommu.c>: use no hardware/software IOMMU at all
+      (e.g. because you have < 3 GB memory).
+      Kernel boot message: "PCI-DMA: Disabling IOMMU"
+
+   2. <arch/x86_64/kernel/pci-gart.c>: AMD GART based hardware IOMMU.
+      Kernel boot message: "PCI-DMA: using GART IOMMU"
+
+   3. <arch/x86_64/kernel/pci-swiotlb.c> : Software IOMMU implementation. Used
+      e.g. if there is no hardware IOMMU in the system and it is need because
+      you have >3GB memory or told the kernel to us it (iommu=soft))
+      Kernel boot message: "PCI-DMA: Using software bounce buffering
+      for IO (SWIOTLB)"
+
+   4. <arch/x86_64/pci-calgary.c> : IBM Calgary hardware IOMMU. Used in IBM
+      pSeries and xSeries servers. This hardware IOMMU supports DMA address
+      mapping with memory protection, etc.
+      Kernel boot message: "PCI-DMA: Using Calgary IOMMU"
+
+ iommu=[<size>][,noagp][,off][,force][,noforce][,leak[=<nr_of_leak_pages>]
+	[,memaper[=<order>]][,merge][,forcesac][,fullflush][,nomerge]
+	[,noaperture][,calgary]
+
+  General iommu options:
+    off                Don't initialize and use any kind of IOMMU.
+    noforce            Don't force hardware IOMMU usage when it is not needed.
+                       (default).
+    force              Force the use of the hardware IOMMU even when it is
+                       not actually needed (e.g. because < 3 GB memory).
+    soft               Use software bounce buffering (SWIOTLB) (default for
+                       Intel machines). This can be used to prevent the usage
+                       of an available hardware IOMMU.
+
+  iommu options only relevant to the AMD GART hardware IOMMU:
+    <size>             Set the size of the remapping area in bytes.
+    allowed            Overwrite iommu off workarounds for specific chipsets.
+    fullflush          Flush IOMMU on each allocation (default).
+    nofullflush        Don't use IOMMU fullflush.
+    leak               Turn on simple iommu leak tracing (only when
+                       CONFIG_IOMMU_LEAK is on). Default number of leak pages
+                       is 20.
+    memaper[=<order>]  Allocate an own aperture over RAM with size 32MB<<order.
+                       (default: order=1, i.e. 64MB)
+    merge              Do scatter-gather (SG) merging. Implies "force"
+                       (experimental).
+    nomerge            Don't do scatter-gather (SG) merging.
+    noaperture         Ask the IOMMU not to touch the aperture for AGP.
+    forcesac           Force single-address cycle (SAC) mode for masks <40bits
+                       (experimental).
+    noagp              Don't initialize the AGP driver and use full aperture.
+    allowdac           Allow double-address cycle (DAC) mode, i.e. DMA >4GB.
+                       DAC is used with 32-bit PCI to push a 64-bit address in
+                       two cycles. When off all DMA over >4GB is forced through
+                       an IOMMU or software bounce buffering.
+    nodac              Forbid DAC mode, i.e. DMA >4GB.
+    panic              Always panic when IOMMU overflows.
+    calgary            Use the Calgary IOMMU if it is available
+
+  iommu options only relevant to the software bounce buffering (SWIOTLB) IOMMU
+  implementation:
+    swiotlb=<pages>[,force]
+    <pages>            Prereserve that many 128K pages for the software IO
+                       bounce buffering.
+    force              Force all IO through the software TLB.
+
+  Settings for the IBM Calgary hardware IOMMU currently found in IBM
+  pSeries and xSeries machines:
+
+    calgary=[64k,128k,256k,512k,1M,2M,4M,8M]
+    calgary=[translate_empty_slots]
+    calgary=[disable=<PCI bus number>]
+    panic              Always panic when IOMMU overflows
 
     64k,...,8M - Set the size of each PCI slot's translation table
     when using the Calgary IOMMU. This is the size of the translation
@@ -234,14 +275,14 @@ IOMMU
 
 Debugging
 
-  oops=panic Always panic on oopses. Default is to just kill the process,
-	     but there is a small probability of deadlocking the machine.
-	     This will also cause panics on machine check exceptions.
-	     Useful together with panic=30 to trigger a reboot.
+  oops=panic	Always panic on oopses. Default is to just kill the process,
+		but there is a small probability of deadlocking the machine.
+		This will also cause panics on machine check exceptions.
+		Useful together with panic=30 to trigger a reboot.
 
-  kstack=N   Print that many words from the kernel stack in oops dumps.
+  kstack=N	Print N words from the kernel stack in oops dumps.
 
-  pagefaulttrace Dump all page faults. Only useful for extreme debugging
+  pagefaulttrace  Dump all page faults. Only useful for extreme debugging
 		and will create a lot of output.
 
   call_trace=[old|both|newfallback|new]
@@ -251,15 +292,8 @@ 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
+Miscellaneous
 
   noreplacement  Don't replace instructions with more appropriate ones
 		 for the CPU. This may be useful on asymmetric MP systems
-		 where some CPU have less capabilities than the others.
+		 where some CPUs have less capabilities than others.

Documentation/x86_64/cpu-hotplug-spec

@@ -2,7 +2,7 @@ Firmware support for CPU hotplug under Linux/x86-64
 ---------------------------------------------------
 
 Linux/x86-64 supports CPU hotplug now. For various reasons Linux wants to
-know in advance boot time the maximum number of CPUs that could be plugged
+know in advance of boot time the maximum number of CPUs that could be plugged
 into the system. ACPI 3.0 currently has no official way to supply
 this information from the firmware to the operating system.
 

Documentation/x86_64/kernel-stacks

@@ -9,9 +9,9 @@ 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
+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 are:
 
 * Interrupt stack.  IRQSTACKSIZE
 
@@ -32,17 +32,17 @@ 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.
+(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
+An IST is selected by a 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)
+(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
@@ -58,17 +58,17 @@ The currently assigned IST stacks are :-
 
   Used for interrupt 12 - Stack Fault Exception (#SS).
 
-  This allows to recover from invalid stack segments. Rarely
+  This allows the CPU 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.
+  Invoked when handling one exception causes another exception. Happens
+  when the kernel is very confused (e.g. kernel stack pointer corrupt).
+  Using a separate stack allows the kernel to recover from it well enough
+  in many cases to still output an oops.
 
 * NMI_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
 

Documentation/x86_64/machinecheck

@@ -0,0 +1,70 @@
+
+Configurable sysfs parameters for the x86-64 machine check code.
+
+Machine checks report internal hardware error conditions detected
+by the CPU. Uncorrected errors typically cause a machine check
+(often with panic), corrected ones cause a machine check log entry.
+
+Machine checks are organized in banks (normally associated with
+a hardware subsystem) and subevents in a bank. The exact meaning
+of the banks and subevent is CPU specific.
+
+mcelog knows how to decode them.
+
+When you see the "Machine check errors logged" message in the system
+log then mcelog should run to collect and decode machine check entries
+from /dev/mcelog. Normally mcelog should be run regularly from a cronjob.
+
+Each CPU has a directory in /sys/devices/system/machinecheck/machinecheckN
+(N = CPU number)
+
+The directory contains some configurable entries:
+
+Entries:
+
+bankNctl
+(N bank number)
+	64bit Hex bitmask enabling/disabling specific subevents for bank N
+	When a bit in the bitmask is zero then the respective
+	subevent will not be reported.
+	By default all events are enabled.
+	Note that BIOS maintain another mask to disable specific events
+	per bank.  This is not visible here
+
+The following entries appear for each CPU, but they are truly shared
+between all CPUs.
+
+check_interval
+	How often to poll for corrected machine check errors, in seconds
+	(Note output is hexademical). Default 5 minutes.
+
+tolerant
+	Tolerance level. When a machine check exception occurs for a non
+	corrected machine check the kernel can take different actions.
+	Since machine check exceptions can happen any time it is sometimes
+	risky for the kernel to kill a process because it defies
+	normal kernel locking rules. The tolerance level configures
+	how hard the kernel tries to recover even at some risk of deadlock.
+
+	0: always panic,
+	1: panic if deadlock possible,
+	2: try to avoid panic,
+   	3: never panic or exit (for testing only)
+
+	Default: 1
+
+	Note this only makes a difference if the CPU allows recovery
+	from a machine check exception. Current x86 CPUs generally do not.
+
+trigger
+	Program to run when a machine check event is detected.
+	This is an alternative to running mcelog regularly from cron
+	and allows to detect events faster.
+
+TBD document entries for AMD threshold interrupt configuration
+
+For more details about the x86 machine check architecture
+see the Intel and AMD architecture manuals from their developer websites.
+
+For more details about the architecture see
+see http://one.firstfloor.org/~andi/mce.pdf

Documentation/x86_64/mm.txt

@@ -3,26 +3,26 @@
 
 Virtual memory map with 4 level page tables:
 
-0000000000000000 - 00007fffffffffff (=47bits) user space, different per mm
+0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
 hole caused by [48:63] sign extension
-ffff800000000000 - ffff80ffffffffff (=40bits) guard hole
-ffff810000000000 - ffffc0ffffffffff (=46bits) direct mapping of all phys. memory
-ffffc10000000000 - ffffc1ffffffffff (=40bits) hole
-ffffc20000000000 - ffffe1ffffffffff (=45bits) vmalloc/ioremap space
+ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
+ffff810000000000 - ffffc0ffffffffff (=46 bits) direct mapping of all phys. memory
+ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
+ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
 ... unused hole ...
-ffffffff80000000 - ffffffff82800000 (=40MB)   kernel text mapping, from phys 0
+ffffffff80000000 - ffffffff82800000 (=40 MB)   kernel text mapping, from phys 0
 ... unused hole ...
-ffffffff88000000 - fffffffffff00000 (=1919MB) module mapping space
+ffffffff88000000 - fffffffffff00000 (=1919 MB) module mapping space
 
-The direct mapping covers all memory in the system upto the highest
+The direct mapping covers all memory in the system up to the highest
 memory address (this means in some cases it can also include PCI memory
-holes)
+holes).
 
 vmalloc space is lazily synchronized into the different PML4 pages of
 the processes using the page fault handler, with init_level4_pgt as
 reference.
 
-Current X86-64 implementations only support 40 bit of address space,
-but we support upto 46bits. This expands into MBZ space in the page tables.
+Current X86-64 implementations only support 40 bits of address space,
+but we support up to 46 bits. This expands into MBZ space in the page tables.
 
 -Andi Kleen, Jul 2004

MAINTAINERS

@@ -3779,6 +3779,7 @@ P:	Andi Kleen
 M:	[email protected]
 L:	[email protected]
 W:	http://www.x86-64.org
+T:	quilt ftp://ftp.firstfloor.org/pub/ak/x86_64/quilt-current
 S:	Maintained
 
 YAM DRIVER FOR AX.25

arch/i386/Kconfig

@@ -203,6 +203,15 @@ config PARAVIRT
 	  However, when run without a hypervisor the kernel is
 	  theoretically slower.  If in doubt, say N.
 
+config VMI
+	bool "VMI Paravirt-ops support"
+	depends on PARAVIRT
+	default y
+	help
+	  VMI provides a paravirtualized interface to multiple hypervisors
+	  include VMware ESX server and Xen by connecting to a ROM module
+	  provided by the hypervisor.
+
 config ACPI_SRAT
 	bool
 	default y
@@ -1263,3 +1272,12 @@ config X86_TRAMPOLINE
 config KTIME_SCALAR
 	bool
 	default y
+
+config NO_IDLE_HZ
+	bool
+	depends on PARAVIRT
+	default y
+	help
+	  Switches the regular HZ timer off when the system is going idle.
+	  This helps a hypervisor detect that the Linux system is idle,
+	  reducing the overhead of idle systems.