Merge branch 'tip/perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/urgent

Documentation/RCU/trace.txt

@@ -1,18 +1,22 @@
 CONFIG_RCU_TRACE debugfs Files and Formats
 
 
-The rcutree implementation of RCU provides debugfs trace output that
-summarizes counters and state.  This information is useful for debugging
-RCU itself, and can sometimes also help to debug abuses of RCU.
-The following sections describe the debugfs files and formats.
+The rcutree and rcutiny implementations of RCU provide debugfs trace
+output that summarizes counters and state.  This information is useful for
+debugging RCU itself, and can sometimes also help to debug abuses of RCU.
+The following sections describe the debugfs files and formats, first
+for rcutree and next for rcutiny.
 
 
-Hierarchical RCU debugfs Files and Formats
+CONFIG_TREE_RCU and CONFIG_TREE_PREEMPT_RCU debugfs Files and Formats
 
-This implementation of RCU provides three debugfs files under the
+These implementations of RCU provides five debugfs files under the
 top-level directory RCU: rcu/rcudata (which displays fields in struct
-rcu_data), rcu/rcugp (which displays grace-period counters), and
-rcu/rcuhier (which displays the struct rcu_node hierarchy).
+rcu_data), rcu/rcudata.csv (which is a .csv spreadsheet version of
+rcu/rcudata), rcu/rcugp (which displays grace-period counters),
+rcu/rcuhier (which displays the struct rcu_node hierarchy), and
+rcu/rcu_pending (which displays counts of the reasons that the
+rcu_pending() function decided that there was core RCU work to do).
 
 The output of "cat rcu/rcudata" looks as follows:
 
@@ -130,7 +134,8 @@ o	"ci" is the number of RCU callbacks that have been invoked for
 	been registered in absence of CPU-hotplug activity.
 
 o	"co" is the number of RCU callbacks that have been orphaned due to
-	this CPU going offline.
+	this CPU going offline.  These orphaned callbacks have been moved
+	to an arbitrarily chosen online CPU.
 
 o	"ca" is the number of RCU callbacks that have been adopted due to
 	other CPUs going offline.  Note that ci+co-ca+ql is the number of
@@ -168,12 +173,12 @@ o	"gpnum" is the number of grace periods that have started.  It is
 
 The output of "cat rcu/rcuhier" looks as follows, with very long lines:
 
-c=6902 g=6903 s=2 jfq=3 j=72c7 nfqs=13142/nfqsng=0(13142) fqlh=6 oqlen=0
+c=6902 g=6903 s=2 jfq=3 j=72c7 nfqs=13142/nfqsng=0(13142) fqlh=6
 1/1 .>. 0:127 ^0    
 3/3 .>. 0:35 ^0    0/0 .>. 36:71 ^1    0/0 .>. 72:107 ^2    0/0 .>. 108:127 ^3    
 3/3f .>. 0:5 ^0    2/3 .>. 6:11 ^1    0/0 .>. 12:17 ^2    0/0 .>. 18:23 ^3    0/0 .>. 24:29 ^4    0/0 .>. 30:35 ^5    0/0 .>. 36:41 ^0    0/0 .>. 42:47 ^1    0/0 .>. 48:53 ^2    0/0 .>. 54:59 ^3    0/0 .>. 60:65 ^4    0/0 .>. 66:71 ^5    0/0 .>. 72:77 ^0    0/0 .>. 78:83 ^1    0/0 .>. 84:89 ^2    0/0 .>. 90:95 ^3    0/0 .>. 96:101 ^4    0/0 .>. 102:107 ^5    0/0 .>. 108:113 ^0    0/0 .>. 114:119 ^1    0/0 .>. 120:125 ^2    0/0 .>. 126:127 ^3    
 rcu_bh:
-c=-226 g=-226 s=1 jfq=-5701 j=72c7 nfqs=88/nfqsng=0(88) fqlh=0 oqlen=0
+c=-226 g=-226 s=1 jfq=-5701 j=72c7 nfqs=88/nfqsng=0(88) fqlh=0
 0/1 .>. 0:127 ^0    
 0/3 .>. 0:35 ^0    0/0 .>. 36:71 ^1    0/0 .>. 72:107 ^2    0/0 .>. 108:127 ^3    
 0/3f .>. 0:5 ^0    0/3 .>. 6:11 ^1    0/0 .>. 12:17 ^2    0/0 .>. 18:23 ^3    0/0 .>. 24:29 ^4    0/0 .>. 30:35 ^5    0/0 .>. 36:41 ^0    0/0 .>. 42:47 ^1    0/0 .>. 48:53 ^2    0/0 .>. 54:59 ^3    0/0 .>. 60:65 ^4    0/0 .>. 66:71 ^5    0/0 .>. 72:77 ^0    0/0 .>. 78:83 ^1    0/0 .>. 84:89 ^2    0/0 .>. 90:95 ^3    0/0 .>. 96:101 ^4    0/0 .>. 102:107 ^5    0/0 .>. 108:113 ^0    0/0 .>. 114:119 ^1    0/0 .>. 120:125 ^2    0/0 .>. 126:127 ^3
@@ -212,11 +217,6 @@ o	"fqlh" is the number of calls to force_quiescent_state() that
 	exited immediately (without even being counted in nfqs above)
 	due to contention on ->fqslock.
 
-o	"oqlen" is the number of callbacks on the "orphan" callback
-	list.  RCU callbacks are placed on this list by CPUs going
-	offline, and are "adopted" either by the CPU helping the outgoing
-	CPU or by the next rcu_barrier*() call, whichever comes first.
-
 o	Each element of the form "1/1 0:127 ^0" represents one struct
 	rcu_node.  Each line represents one level of the hierarchy, from
 	root to leaves.  It is best to think of the rcu_data structures
@@ -326,3 +326,115 @@ o	"nn" is the number of times that this CPU needed nothing.  Alert
 	readers will note that the rcu "nn" number for a given CPU very
 	closely matches the rcu_bh "np" number for that same CPU.  This
 	is due to short-circuit evaluation in rcu_pending().
+
+
+CONFIG_TINY_RCU and CONFIG_TINY_PREEMPT_RCU debugfs Files and Formats
+
+These implementations of RCU provides a single debugfs file under the
+top-level directory RCU, namely rcu/rcudata, which displays fields in
+rcu_bh_ctrlblk, rcu_sched_ctrlblk and, for CONFIG_TINY_PREEMPT_RCU,
+rcu_preempt_ctrlblk.
+
+The output of "cat rcu/rcudata" is as follows:
+
+rcu_preempt: qlen=24 gp=1097669 g197/p197/c197 tasks=...
+             ttb=. btg=no ntb=184 neb=0 nnb=183 j=01f7 bt=0274
+             normal balk: nt=1097669 gt=0 bt=371 b=0 ny=25073378 nos=0
+             exp balk: bt=0 nos=0
+rcu_sched: qlen: 0
+rcu_bh: qlen: 0
+
+This is split into rcu_preempt, rcu_sched, and rcu_bh sections, with the
+rcu_preempt section appearing only in CONFIG_TINY_PREEMPT_RCU builds.
+The last three lines of the rcu_preempt section appear only in
+CONFIG_RCU_BOOST kernel builds.  The fields are as follows:
+
+o	"qlen" is the number of RCU callbacks currently waiting either
+	for an RCU grace period or waiting to be invoked.  This is the
+	only field present for rcu_sched and rcu_bh, due to the
+	short-circuiting of grace period in those two cases.
+
+o	"gp" is the number of grace periods that have completed.
+
+o	"g197/p197/c197" displays the grace-period state, with the
+	"g" number being the number of grace periods that have started
+	(mod 256), the "p" number being the number of grace periods
+	that the CPU has responded to (also mod 256), and the "c"
+	number being the number of grace periods that have completed
+	(once again mode 256).
+
+	Why have both "gp" and "g"?  Because the data flowing into
+	"gp" is only present in a CONFIG_RCU_TRACE kernel.
+
+o	"tasks" is a set of bits.  The first bit is "T" if there are
+	currently tasks that have recently blocked within an RCU
+	read-side critical section, the second bit is "N" if any of the
+	aforementioned tasks are blocking the current RCU grace period,
+	and the third bit is "E" if any of the aforementioned tasks are
+	blocking the current expedited grace period.  Each bit is "."
+	if the corresponding condition does not hold.
+
+o	"ttb" is a single bit.  It is "B" if any of the blocked tasks
+	need to be priority boosted and "." otherwise.
+
+o	"btg" indicates whether boosting has been carried out during
+	the current grace period, with "exp" indicating that boosting
+	is in progress for an expedited grace period, "no" indicating
+	that boosting has not yet started for a normal grace period,
+	"begun" indicating that boosting has bebug for a normal grace
+	period, and "done" indicating that boosting has completed for
+	a normal grace period.
+
+o	"ntb" is the total number of tasks subjected to RCU priority boosting
+	periods since boot.
+
+o	"neb" is the number of expedited grace periods that have had
+	to resort to RCU priority boosting since boot.
+
+o	"nnb" is the number of normal grace periods that have had
+	to resort to RCU priority boosting since boot.
+
+o	"j" is the low-order 12 bits of the jiffies counter in hexadecimal.
+
+o	"bt" is the low-order 12 bits of the value that the jiffies counter
+	will have at the next time that boosting is scheduled to begin.
+
+o	In the line beginning with "normal balk", the fields are as follows:
+
+	o	"nt" is the number of times that the system balked from
+		boosting because there were no blocked tasks to boost.
+		Note that the system will balk from boosting even if the
+		grace period is overdue when the currently running task
+		is looping within an RCU read-side critical section.
+		There is no point in boosting in this case, because
+		boosting a running task won't make it run any faster.
+
+	o	"gt" is the number of times that the system balked
+		from boosting because, although there were blocked tasks,
+		none of them were preventing the current grace period
+		from completing.
+
+	o	"bt" is the number of times that the system balked
+		from boosting because boosting was already in progress.
+
+	o	"b" is the number of times that the system balked from
+		boosting because boosting had already completed for
+		the grace period in question.
+
+	o	"ny" is the number of times that the system balked from
+		boosting because it was not yet time to start boosting
+		the grace period in question.
+
+	o	"nos" is the number of times that the system balked from
+		boosting for inexplicable ("not otherwise specified")
+		reasons.  This can actually happen due to races involving
+		increments of the jiffies counter.
+
+o	In the line beginning with "exp balk", the fields are as follows:
+
+	o	"bt" is the number of times that the system balked from
+		boosting because there were no blocked tasks to boost.
+
+	o	"nos" is the number of times that the system balked from
+		 boosting for inexplicable ("not otherwise specified")
+		 reasons.

Documentation/dontdiff

@@ -62,6 +62,10 @@ aic7*reg_print.c*
 aic7*seq.h*
 aicasm
 aicdb.h*
+altivec1.c
+altivec2.c
+altivec4.c
+altivec8.c
 asm-offsets.h
 asm_offsets.h
 autoconf.h*
@@ -76,6 +80,7 @@ btfixupprep
 build
 bvmlinux
 bzImage*
+capflags.c
 classlist.h*
 comp*.log
 compile.h*
@@ -94,6 +99,7 @@ devlist.h*
 docproc
 elf2ecoff
 elfconfig.h*
+evergreen_reg_safe.h
 fixdep
 flask.h
 fore200e_mkfirm
@@ -108,9 +114,16 @@ genksyms
 *_gray256.c
 ihex2fw
 ikconfig.h*
+inat-tables.c
 initramfs_data.cpio
 initramfs_data.cpio.gz
 initramfs_list
+int16.c
+int1.c
+int2.c
+int32.c
+int4.c
+int8.c
 kallsyms
 kconfig
 keywords.c
@@ -140,6 +153,7 @@ mkprep
 mktables
 mktree
 modpost
+modules.builtin
 modules.order
 modversions.h*
 ncscope.*
@@ -153,14 +167,23 @@ pca200e.bin
 pca200e_ecd.bin2
 piggy.gz
 piggyback
+piggy.S
 pnmtologo
 ppc_defs.h*
 pss_boot.h
 qconf
+r100_reg_safe.h
+r200_reg_safe.h
+r300_reg_safe.h
+r420_reg_safe.h
+r600_reg_safe.h
 raid6altivec*.c
 raid6int*.c
 raid6tables.c
 relocs
+rn50_reg_safe.h
+rs600_reg_safe.h
+rv515_reg_safe.h
 series
 setup
 setup.bin
@@ -169,6 +192,7 @@ sImage
 sm_tbl*
 split-include
 syscalltab.h
+tables.c
 tags
 tftpboot.img
 timeconst.h
@@ -190,6 +214,7 @@ vmlinux
 vmlinux-*
 vmlinux.aout
 vmlinux.lds
+voffset.h
 vsyscall.lds
 vsyscall_32.lds
 wanxlfw.inc
@@ -200,3 +225,4 @@ wakeup.elf
 wakeup.lds
 zImage*
 zconf.hash.c
+zoffset.h

Documentation/kernel-docs.txt

@@ -537,7 +537,7 @@
        Notes: Further information in
        http://www.oreilly.com/catalog/linuxdrive2/
 
-     * Title: "Linux Device Drivers, 3nd Edition"
+     * Title: "Linux Device Drivers, 3rd Edition"
        Authors: Jonathan Corbet, Alessandro Rubini, and Greg Kroah-Hartman
        Publisher: O'Reilly & Associates.
        Date: 2005.
@@ -592,14 +592,6 @@
        Pages: 600.
        ISBN: 0-13-101908-2
 
-     * Title:  "The  Design  and Implementation of the 4.4 BSD UNIX
-       Operating System"
-       Author: Marshall Kirk McKusick, Keith Bostic, Michael J. Karels,
-       John S. Quarterman.
-       Publisher: Addison-Wesley.
-       Date: 1996.
-       ISBN: 0-201-54979-4
-
      * Title: "Programming for the real world - POSIX.4"
        Author: Bill O. Gallmeister.
        Publisher: O'Reilly & Associates, Inc..
@@ -610,28 +602,13 @@
        POSIX. Good reference.
 
      * Title:  "UNIX  Systems  for  Modern Architectures: Symmetric
-       Multiprocesssing and Caching for Kernel Programmers"
+       Multiprocessing and Caching for Kernel Programmers"
        Author: Curt Schimmel.
        Publisher: Addison Wesley.
        Date: June, 1994.
        Pages: 432.
        ISBN: 0-201-63338-8
 
-     * Title:  "The  Design  and Implementation of the 4.3 BSD UNIX
-       Operating System"
-       Author: Samuel J. Leffler, Marshall Kirk McKusick, Michael J.
-       Karels, John S. Quarterman.
-       Publisher: Addison-Wesley.
-       Date: 1989 (reprinted with corrections on October, 1990).
-       ISBN: 0-201-06196-1
-
-     * Title: "The Design of the UNIX Operating System"
-       Author: Maurice J. Bach.
-       Publisher: Prentice Hall.
-       Date: 1986.
-       Pages: 471.
-       ISBN: 0-13-201757-1
-
      MISCELLANEOUS:
 
      * Name: linux/Documentation

Documentation/kernel-parameters.txt

@@ -1614,6 +1614,8 @@ and is between 256 and 4096 characters. It is defined in the file
 	noapic		[SMP,APIC] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 
+	noautogroup	Disable scheduler automatic task group creation.
+
 	nobats		[PPC] Do not use BATs for mapping kernel lowmem
 			on "Classic" PPC cores.
 
@@ -2459,12 +2461,13 @@ and is between 256 and 4096 characters. It is defined in the file
 			to facilitate early boot debugging.
 			See also Documentation/trace/events.txt
 
-	tsc=		Disable clocksource-must-verify flag for TSC.
+	tsc=		Disable clocksource stability checks 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.
+			disables clocksource verification at runtime, as well
+			as the stability checks done at bootup.	Used to enable
+			high-resolution timer mode on older hardware, and in
+			virtualized environment.
 			[x86] noirqtime: Do not use TSC to do irq accounting.
 			Used to run time disable IRQ_TIME_ACCOUNTING on any
 			platforms where RDTSC is slow and this accounting

Documentation/x86/boot.txt

@@ -600,6 +600,7 @@ Protocol:	2.07+
   0x00000001	lguest
   0x00000002	Xen
   0x00000003	Moorestown MID
+  0x00000004	CE4100 TV Platform
 
 Field name:	hardware_subarch_data
 Type:		write (subarch-dependent)

MAINTAINERS

@@ -2812,6 +2812,10 @@ M:	Thomas Gleixner <tglx@linutronix.de>
 S:	Maintained
 F:	Documentation/timers/
 F:	kernel/hrtimer.c
+F:	kernel/time/clockevents.c
+F:	kernel/time/tick*.*
+F:	kernel/time/timer_*.c
+F	include/linux/clockevents.h
 F:	include/linux/hrtimer.h
 
 HIGH-SPEED SCC DRIVER FOR AX.25
@@ -5142,6 +5146,18 @@ L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Supported
 F:	sound/soc/s3c24xx
 
+TIMEKEEPING, NTP
+M:	John Stultz <johnstul@us.ibm.com>
+M:	Thomas Gleixner <tglx@linutronix.de>
+S:	Supported
+F:	include/linux/clocksource.h
+F:	include/linux/time.h
+F:	include/linux/timex.h
+F:	include/linux/timekeeping.h
+F:	kernel/time/clocksource.c
+F:	kernel/time/time*.c
+F:	kernel/time/ntp.c
+
 TLG2300 VIDEO4LINUX-2 DRIVER
 M:	Huang Shijie <shijie8@gmail.com>
 M:	Kang Yong <kangyong@telegent.com>

arch/Kconfig

@@ -175,4 +175,7 @@ config HAVE_PERF_EVENTS_NMI
 config HAVE_ARCH_JUMP_LABEL
 	bool
 
+config HAVE_ARCH_MUTEX_CPU_RELAX
+	bool
+
 source "kernel/gcov/Kconfig"

arch/s390/Kconfig

@@ -99,6 +99,7 @@ config S390
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
 	select HAVE_GET_USER_PAGES_FAST
+	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select ARCH_INLINE_SPIN_TRYLOCK
 	select ARCH_INLINE_SPIN_TRYLOCK_BH
 	select ARCH_INLINE_SPIN_LOCK

arch/s390/include/asm/mutex.h

@@ -7,3 +7,5 @@
  */
 
 #include <asm-generic/mutex-dec.h>
+
+#define arch_mutex_cpu_relax()	barrier()

arch/x86/Kconfig

@@ -377,6 +377,18 @@ config X86_ELAN
 
 	  If unsure, choose "PC-compatible" instead.
 
+config X86_INTEL_CE
+	bool "CE4100 TV platform"
+	depends on PCI
+	depends on PCI_GODIRECT
+	depends on X86_32
+	depends on X86_EXTENDED_PLATFORM
+	select X86_REBOOTFIXUPS
+	---help---
+	  Select for the Intel CE media processor (CE4100) SOC.
+	  This option compiles in support for the CE4100 SOC for settop
+	  boxes and media devices.
+
 config X86_MRST
        bool "Moorestown MID platform"
 	depends on PCI
@@ -385,6 +397,10 @@ config X86_MRST
 	depends on X86_EXTENDED_PLATFORM
 	depends on X86_IO_APIC
 	select APB_TIMER
+	select I2C
+	select SPI
+	select INTEL_SCU_IPC
+	select X86_PLATFORM_DEVICES
 	---help---
 	  Moorestown is Intel's Low Power Intel Architecture (LPIA) based Moblin
 	  Internet Device(MID) platform. Moorestown consists of two chips:
@@ -466,6 +482,19 @@ config X86_ES7000
 	  Support for Unisys ES7000 systems.  Say 'Y' here if this kernel is
 	  supposed to run on an IA32-based Unisys ES7000 system.
 
+config X86_32_IRIS
+	tristate "Eurobraille/Iris poweroff module"
+	depends on X86_32
+	---help---
+	  The Iris machines from EuroBraille do not have APM or ACPI support
+	  to shut themselves down properly.  A special I/O sequence is
+	  needed to do so, which is what this module does at
+	  kernel shutdown.
+
+	  This is only for Iris machines from EuroBraille.
+
+	  If unused, say N.
+
 config SCHED_OMIT_FRAME_POINTER
 	def_bool y
 	prompt "Single-depth WCHAN output"
@@ -1141,16 +1170,16 @@ config NUMA
 comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
 	depends on X86_32 && X86_SUMMIT && (!HIGHMEM64G || !ACPI)
 
-config K8_NUMA
+config AMD_NUMA
 	def_bool y
 	prompt "Old style AMD Opteron NUMA detection"
 	depends on X86_64 && NUMA && PCI
 	---help---
-	  Enable K8 NUMA node topology detection.  You should say Y here if
-	  you have a multi processor AMD K8 system. This uses an old
-	  method to read the NUMA configuration directly from the builtin
-	  Northbridge of Opteron. It is recommended to use X86_64_ACPI_NUMA
-	  instead, which also takes priority if both are compiled in.
+	  Enable AMD NUMA node topology detection.  You should say Y here if
+	  you have a multi processor AMD system. This uses an old method to
+	  read the NUMA configuration directly from the builtin Northbridge
+	  of Opteron. It is recommended to use X86_64_ACPI_NUMA instead,
+	  which also takes priority if both are compiled in.
 
 config X86_64_ACPI_NUMA
 	def_bool y

arch/x86/Kconfig.debug

@@ -117,6 +117,17 @@ config DEBUG_RODATA_TEST
 	  feature as well as for the change_page_attr() infrastructure.
 	  If in doubt, say "N"
 
+config DEBUG_SET_MODULE_RONX
+	bool "Set loadable kernel module data as NX and text as RO"
+	depends on MODULES
+	---help---
+	  This option helps catch unintended modifications to loadable
+	  kernel module's text and read-only data. It also prevents execution
+	  of module data. Such protection may interfere with run-time code
+	  patching and dynamic kernel tracing - and they might also protect
+	  against certain classes of kernel exploits.
+	  If in doubt, say "N".
+
 config DEBUG_NX_TEST
 	tristate "Testcase for the NX non-executable stack feature"
 	depends on DEBUG_KERNEL && m

arch/x86/boot/compressed/head_64.S

@@ -182,7 +182,7 @@ no_longmode:
 	hlt
 	jmp     1b
 
-#include "../../kernel/verify_cpu_64.S"
+#include "../../kernel/verify_cpu.S"
 
 	/*
 	 * Be careful here startup_64 needs to be at a predictable

arch/x86/include/asm/alternative.h

@@ -66,6 +66,7 @@ extern void alternatives_smp_module_add(struct module *mod, char *name,
 extern void alternatives_smp_module_del(struct module *mod);
 extern void alternatives_smp_switch(int smp);
 extern int alternatives_text_reserved(void *start, void *end);
+extern bool skip_smp_alternatives;
 #else
 static inline void alternatives_smp_module_add(struct module *mod, char *name,
 					       void *locks, void *locks_end,

arch/x86/include/asm/amd_nb.h

@@ -3,36 +3,53 @@
 
 #include <linux/pci.h>
 
-extern struct pci_device_id k8_nb_ids[];
+extern struct pci_device_id amd_nb_misc_ids[];
 struct bootnode;
 
-extern int early_is_k8_nb(u32 value);
-extern int cache_k8_northbridges(void);
-extern void k8_flush_garts(void);
-extern int k8_get_nodes(struct bootnode *nodes);
-extern int k8_numa_init(unsigned long start_pfn, unsigned long end_pfn);
-extern int k8_scan_nodes(void);
+extern int early_is_amd_nb(u32 value);
+extern int amd_cache_northbridges(void);
+extern void amd_flush_garts(void);
+extern int amd_get_nodes(struct bootnode *nodes);
+extern int amd_numa_init(unsigned long start_pfn, unsigned long end_pfn);
+extern int amd_scan_nodes(void);
 
-struct k8_northbridge_info {
+struct amd_northbridge {
+	struct pci_dev *misc;
+};
+
+struct amd_northbridge_info {
 	u16 num;
-	u8 gart_supported;
-	struct pci_dev **nb_misc;
+	u64 flags;
+	struct amd_northbridge *nb;
 };
-extern struct k8_northbridge_info k8_northbridges;
+extern struct amd_northbridge_info amd_northbridges;
+
+#define AMD_NB_GART			0x1
+#define AMD_NB_L3_INDEX_DISABLE		0x2
 
 #ifdef CONFIG_AMD_NB
 
-static inline struct pci_dev *node_to_k8_nb_misc(int node)
+static inline int amd_nb_num(void)
 {
-	return (node < k8_northbridges.num) ? k8_northbridges.nb_misc[node] : NULL;
+	return amd_northbridges.num;
 }
 
-#else
+static inline int amd_nb_has_feature(int feature)
+{
+	return ((amd_northbridges.flags & feature) == feature);
+}
 
-static inline struct pci_dev *node_to_k8_nb_misc(int node)
+static inline struct amd_northbridge *node_to_amd_nb(int node)
 {
-	return NULL;
+	return (node < amd_northbridges.num) ? &amd_northbridges.nb[node] : NULL;
 }
+
+#else
+
+#define amd_nb_num(x)		0
+#define amd_nb_has_feature(x)	false
+#define node_to_amd_nb(x)	NULL
+
 #endif
 
 

arch/x86/include/asm/apic.h

@@ -238,6 +238,7 @@ extern void setup_boot_APIC_clock(void);
 extern void setup_secondary_APIC_clock(void);
 extern int APIC_init_uniprocessor(void);
 extern void enable_NMI_through_LVT0(void);
+extern int apic_force_enable(void);
 
 /*
  * On 32bit this is mach-xxx local

arch/x86/include/asm/apicdef.h

@@ -145,6 +145,7 @@
 
 #ifdef CONFIG_X86_32
 # define MAX_IO_APICS 64
+# define MAX_LOCAL_APIC 256
 #else
 # define MAX_IO_APICS 128
 # define MAX_LOCAL_APIC 32768

arch/x86/include/asm/bootparam.h

@@ -124,6 +124,7 @@ enum {
 	X86_SUBARCH_LGUEST,
 	X86_SUBARCH_XEN,
 	X86_SUBARCH_MRST,
+	X86_SUBARCH_CE4100,
 	X86_NR_SUBARCHS,
 };
 

arch/x86/include/asm/fixmap.h

@@ -117,6 +117,10 @@ enum fixed_addresses {
 	FIX_TEXT_POKE1,	/* reserve 2 pages for text_poke() */
 	FIX_TEXT_POKE0, /* first page is last, because allocation is backward */
 	__end_of_permanent_fixed_addresses,
+
+#ifdef	CONFIG_X86_MRST
+	FIX_LNW_VRTC,
+#endif
 	/*
 	 * 256 temporary boot-time mappings, used by early_ioremap(),
 	 * before ioremap() is functional.

arch/x86/include/asm/i387.h

@@ -93,6 +93,17 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 	int err;
 
 	/* See comment in fxsave() below. */
+#ifdef CONFIG_AS_FXSAVEQ
+	asm volatile("1:  fxrstorq %[fx]\n\t"
+		     "2:\n"
+		     ".section .fixup,\"ax\"\n"
+		     "3:  movl $-1,%[err]\n"
+		     "    jmp  2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [err] "=r" (err)
+		     : [fx] "m" (*fx), "0" (0));
+#else
 	asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
 		     "2:\n"
 		     ".section .fixup,\"ax\"\n"
@@ -102,6 +113,7 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 		     _ASM_EXTABLE(1b, 3b)
 		     : [err] "=r" (err)
 		     : [fx] "R" (fx), "m" (*fx), "0" (0));
+#endif
 	return err;
 }
 
@@ -119,6 +131,17 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 		return -EFAULT;
 
 	/* See comment in fxsave() below. */
+#ifdef CONFIG_AS_FXSAVEQ
+	asm volatile("1:  fxsaveq %[fx]\n\t"
+		     "2:\n"
+		     ".section .fixup,\"ax\"\n"
+		     "3:  movl $-1,%[err]\n"
+		     "    jmp  2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [err] "=r" (err), [fx] "=m" (*fx)
+		     : "0" (0));
+#else
 	asm volatile("1:  rex64/fxsave (%[fx])\n\t"
 		     "2:\n"
 		     ".section .fixup,\"ax\"\n"
@@ -128,6 +151,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 		     _ASM_EXTABLE(1b, 3b)
 		     : [err] "=r" (err), "=m" (*fx)
 		     : [fx] "R" (fx), "0" (0));
+#endif
 	if (unlikely(err) &&
 	    __clear_user(fx, sizeof(struct i387_fxsave_struct)))
 		err = -EFAULT;

arch/x86/include/asm/io_apic.h

@@ -159,7 +159,7 @@ struct io_apic_irq_attr;
 extern int io_apic_set_pci_routing(struct device *dev, int irq,
 		 struct io_apic_irq_attr *irq_attr);
 void setup_IO_APIC_irq_extra(u32 gsi);
-extern void ioapic_init_mappings(void);
+extern void ioapic_and_gsi_init(void);
 extern void ioapic_insert_resources(void);
 
 extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
@@ -168,10 +168,9 @@ extern int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 extern void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 
-extern void probe_nr_irqs_gsi(void);
 extern int get_nr_irqs_gsi(void);
-
 extern void setup_ioapic_ids_from_mpc(void);
+extern void setup_ioapic_ids_from_mpc_nocheck(void);
 
 struct mp_ioapic_gsi{
 	u32 gsi_base;
@@ -189,9 +188,8 @@ extern void __init pre_init_apic_IRQ0(void);
 #define io_apic_assign_pci_irqs 0
 #define setup_ioapic_ids_from_mpc x86_init_noop
 static const int timer_through_8259 = 0;
-static inline void ioapic_init_mappings(void)	{ }
+static inline void ioapic_and_gsi_init(void) { }
 static inline void ioapic_insert_resources(void) { }
-static inline void probe_nr_irqs_gsi(void)	{ }
 #define gsi_top (NR_IRQS_LEGACY)
 static inline int mp_find_ioapic(u32 gsi) { return 0; }
 

arch/x86/include/asm/mce.h

@@ -223,6 +223,9 @@ void intel_init_thermal(struct cpuinfo_x86 *c);
 
 void mce_log_therm_throt_event(__u64 status);
 
+/* Interrupt Handler for core thermal thresholds */
+extern int (*platform_thermal_notify)(__u64 msr_val);
+
 #ifdef CONFIG_X86_THERMAL_VECTOR
 extern void mcheck_intel_therm_init(void);
 #else

arch/x86/include/asm/microcode.h

@@ -48,6 +48,12 @@ static inline struct microcode_ops * __init init_intel_microcode(void)
 
 #ifdef CONFIG_MICROCODE_AMD
 extern struct microcode_ops * __init init_amd_microcode(void);
+
+static inline void get_ucode_data(void *to, const u8 *from, size_t n)
+{
+	memcpy(to, from, n);
+}
+
 #else
 static inline struct microcode_ops * __init init_amd_microcode(void)
 {

arch/x86/include/asm/mpspec.h

@@ -5,8 +5,9 @@
 
 #include <asm/mpspec_def.h>
 #include <asm/x86_init.h>
+#include <asm/apicdef.h>
 
-extern int apic_version[MAX_APICS];
+extern int apic_version[];
 extern int pic_mode;
 
 #ifdef CONFIG_X86_32
@@ -107,7 +108,7 @@ extern int mp_register_gsi(struct device *dev, u32 gsi, int edge_level,
 				 int active_high_low);
 #endif /* CONFIG_ACPI */
 
-#define PHYSID_ARRAY_SIZE	BITS_TO_LONGS(MAX_APICS)
+#define PHYSID_ARRAY_SIZE	BITS_TO_LONGS(MAX_LOCAL_APIC)
 
 struct physid_mask {
 	unsigned long mask[PHYSID_ARRAY_SIZE];
@@ -122,31 +123,31 @@ typedef struct physid_mask physid_mask_t;
 	test_and_set_bit(physid, (map).mask)
 
 #define physids_and(dst, src1, src2)					\
-	bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
+	bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC)
 
 #define physids_or(dst, src1, src2)					\
-	bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
+	bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC)
 
 #define physids_clear(map)					\
-	bitmap_zero((map).mask, MAX_APICS)
+	bitmap_zero((map).mask, MAX_LOCAL_APIC)
 
 #define physids_complement(dst, src)				\
-	bitmap_complement((dst).mask, (src).mask, MAX_APICS)
+	bitmap_complement((dst).mask, (src).mask, MAX_LOCAL_APIC)
 
 #define physids_empty(map)					\
-	bitmap_empty((map).mask, MAX_APICS)
+	bitmap_empty((map).mask, MAX_LOCAL_APIC)
 
 #define physids_equal(map1, map2)				\
-	bitmap_equal((map1).mask, (map2).mask, MAX_APICS)
+	bitmap_equal((map1).mask, (map2).mask, MAX_LOCAL_APIC)
 
 #define physids_weight(map)					\
-	bitmap_weight((map).mask, MAX_APICS)
+	bitmap_weight((map).mask, MAX_LOCAL_APIC)
 
 #define physids_shift_right(d, s, n)				\
-	bitmap_shift_right((d).mask, (s).mask, n, MAX_APICS)
+	bitmap_shift_right((d).mask, (s).mask, n, MAX_LOCAL_APIC)
 
 #define physids_shift_left(d, s, n)				\
-	bitmap_shift_left((d).mask, (s).mask, n, MAX_APICS)
+	bitmap_shift_left((d).mask, (s).mask, n, MAX_LOCAL_APIC)
 
 static inline unsigned long physids_coerce(physid_mask_t *map)
 {
@@ -159,14 +160,6 @@ static inline void physids_promote(unsigned long physids, physid_mask_t *map)
 	map->mask[0] = physids;
 }
 
-/* Note: will create very large stack frames if physid_mask_t is big */
-#define physid_mask_of_physid(physid)					\
-	({								\
-		physid_mask_t __physid_mask = PHYSID_MASK_NONE;		\
-		physid_set(physid, __physid_mask);			\
-		__physid_mask;						\
-	})
-
 static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map)
 {
 	physids_clear(*map);

arch/x86/include/asm/mpspec_def.h

@@ -15,13 +15,6 @@
 
 #ifdef CONFIG_X86_32
 # define MAX_MPC_ENTRY 1024
-# define MAX_APICS      256
-#else
-# if NR_CPUS <= 255
-#  define MAX_APICS     255
-# else
-#  define MAX_APICS   32768
-# endif
 #endif
 
 /* Intel MP Floating Pointer Structure */

arch/x86/include/asm/mrst-vrtc.h

@@ -0,0 +1,9 @@
+#ifndef _MRST_VRTC_H
+#define _MRST_VRTC_H
+
+extern unsigned char vrtc_cmos_read(unsigned char reg);
+extern void vrtc_cmos_write(unsigned char val, unsigned char reg);
+extern unsigned long vrtc_get_time(void);
+extern int vrtc_set_mmss(unsigned long nowtime);
+
+#endif

arch/x86/include/asm/mrst.h

@@ -14,7 +14,9 @@
 #include <linux/sfi.h>
 
 extern int pci_mrst_init(void);
-int __init sfi_parse_mrtc(struct sfi_table_header *table);
+extern int __init sfi_parse_mrtc(struct sfi_table_header *table);
+extern int sfi_mrtc_num;
+extern struct sfi_rtc_table_entry sfi_mrtc_array[];
 
 /*
  * Medfield is the follow-up of Moorestown, it combines two chip solution into
@@ -50,4 +52,14 @@ extern void mrst_early_console_init(void);
 
 extern struct console early_hsu_console;
 extern void hsu_early_console_init(void);
+
+extern void intel_scu_devices_create(void);
+extern void intel_scu_devices_destroy(void);
+
+/* VRTC timer */
+#define MRST_VRTC_MAP_SZ	(1024)
+/*#define MRST_VRTC_PGOFFSET	(0xc00) */
+
+extern void mrst_rtc_init(void);
+
 #endif /* _ASM_X86_MRST_H */

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

@@ -257,6 +257,18 @@
 #define PACKAGE_THERM_INT_LOW_ENABLE		(1 << 1)
 #define PACKAGE_THERM_INT_PLN_ENABLE		(1 << 24)
 
+/* Thermal Thresholds Support */
+#define THERM_INT_THRESHOLD0_ENABLE    (1 << 15)
+#define THERM_SHIFT_THRESHOLD0        8
+#define THERM_MASK_THRESHOLD0          (0x7f << THERM_SHIFT_THRESHOLD0)
+#define THERM_INT_THRESHOLD1_ENABLE    (1 << 23)
+#define THERM_SHIFT_THRESHOLD1        16
+#define THERM_MASK_THRESHOLD1          (0x7f << THERM_SHIFT_THRESHOLD1)
+#define THERM_STATUS_THRESHOLD0        (1 << 6)
+#define THERM_LOG_THRESHOLD0           (1 << 7)
+#define THERM_STATUS_THRESHOLD1        (1 << 8)
+#define THERM_LOG_THRESHOLD1           (1 << 9)
+
 /* MISC_ENABLE bits: architectural */
 #define MSR_IA32_MISC_ENABLE_FAST_STRING	(1ULL << 0)
 #define MSR_IA32_MISC_ENABLE_TCC		(1ULL << 1)

arch/x86/include/asm/paravirt.h

@@ -112,7 +112,7 @@ static inline void arch_safe_halt(void)
 
 static inline void halt(void)
 {
-	PVOP_VCALL0(pv_irq_ops.safe_halt);
+	PVOP_VCALL0(pv_irq_ops.halt);
 }
 
 static inline void wbinvd(void)

arch/x86/include/asm/pci.h

@@ -65,6 +65,7 @@ extern unsigned long pci_mem_start;
 
 #define PCIBIOS_MIN_CARDBUS_IO	0x4000
 
+extern int pcibios_enabled;
 void pcibios_config_init(void);
 struct pci_bus *pcibios_scan_root(int bus);
 

arch/x86/include/asm/setup.h

@@ -53,6 +53,12 @@ extern void x86_mrst_early_setup(void);
 static inline void x86_mrst_early_setup(void) { }
 #endif
 
+#ifdef CONFIG_X86_INTEL_CE
+extern void x86_ce4100_early_setup(void);
+#else
+static inline void x86_ce4100_early_setup(void) { }
+#endif
+
 #ifndef _SETUP
 
 /*

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

@@ -26,20 +26,22 @@
  * BAU_SB_DESCRIPTOR_BASE register, set 1 is located at BASE + 512,
  * set 2 is at BASE + 2*512, set 3 at BASE + 3*512, and so on.
  *
- * We will use 31 sets, one for sending BAU messages from each of the 32
+ * We will use one set for sending BAU messages from each of the
  * cpu's on the uvhub.
  *
  * TLB shootdown will use the first of the 8 descriptors of each set.
  * Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set).
  */
 
+#define MAX_CPUS_PER_UVHUB		64
+#define MAX_CPUS_PER_SOCKET		32
+#define UV_ADP_SIZE			64 /* hardware-provided max. */
+#define UV_CPUS_PER_ACT_STATUS		32 /* hardware-provided max. */
 #define UV_ITEMS_PER_DESCRIPTOR		8
 /* the 'throttle' to prevent the hardware stay-busy bug */
 #define MAX_BAU_CONCURRENT		3
-#define UV_CPUS_PER_ACT_STATUS		32
 #define UV_ACT_STATUS_MASK		0x3
 #define UV_ACT_STATUS_SIZE		2
-#define UV_ADP_SIZE			32
 #define UV_DISTRIBUTION_SIZE		256
 #define UV_SW_ACK_NPENDING		8
 #define UV_NET_ENDPOINT_INTD		0x38
@@ -100,7 +102,6 @@
  * number of destination side software ack resources
  */
 #define DEST_NUM_RESOURCES		8
-#define MAX_CPUS_PER_NODE		32
 /*
  * completion statuses for sending a TLB flush message
  */

arch/x86/kernel/Makefile

@@ -85,7 +85,6 @@ obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_VM86)		+= vm86_32.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
-obj-$(CONFIG_EARLY_PRINTK_MRST)	+= early_printk_mrst.o
 
 obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
 obj-$(CONFIG_APB_TIMER)		+= apb_timer.o

arch/x86/kernel/acpi/boot.c

@@ -198,6 +198,11 @@ static void __cpuinit acpi_register_lapic(int id, u8 enabled)
 {
 	unsigned int ver = 0;
 
+	if (id >= (MAX_LOCAL_APIC-1)) {
+		printk(KERN_INFO PREFIX "skipped apicid that is too big\n");
+		return;
+	}
+
 	if (!enabled) {
 		++disabled_cpus;
 		return;
@@ -910,13 +915,13 @@ static int __init acpi_parse_madt_lapic_entries(void)
 	acpi_register_lapic_address(acpi_lapic_addr);
 
 	count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC,
-				      acpi_parse_sapic, MAX_APICS);
+				      acpi_parse_sapic, MAX_LOCAL_APIC);
 
 	if (!count) {
 		x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC,
-						acpi_parse_x2apic, MAX_APICS);
+					acpi_parse_x2apic, MAX_LOCAL_APIC);
 		count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC,
-					      acpi_parse_lapic, MAX_APICS);
+					acpi_parse_lapic, MAX_LOCAL_APIC);
 	}
 	if (!count && !x2count) {
 		printk(KERN_ERR PREFIX "No LAPIC entries present\n");

arch/x86/kernel/alternative.c

@@ -353,6 +353,7 @@ void __init_or_module alternatives_smp_module_del(struct module *mod)
 	mutex_unlock(&smp_alt);
 }
 
+bool skip_smp_alternatives;
 void alternatives_smp_switch(int smp)
 {
 	struct smp_alt_module *mod;
@@ -368,7 +369,7 @@ void alternatives_smp_switch(int smp)
 	printk("lockdep: fixing up alternatives.\n");
 #endif
 
-	if (noreplace_smp || smp_alt_once)
+	if (noreplace_smp || smp_alt_once || skip_smp_alternatives)
 		return;
 	BUG_ON(!smp && (num_online_cpus() > 1));
 

arch/x86/kernel/amd_nb.c

@@ -12,95 +12,116 @@
 
 static u32 *flush_words;
 
-struct pci_device_id k8_nb_ids[] = {
+struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_MISC) },
 	{}
 };
-EXPORT_SYMBOL(k8_nb_ids);
+EXPORT_SYMBOL(amd_nb_misc_ids);
 
-struct k8_northbridge_info k8_northbridges;
-EXPORT_SYMBOL(k8_northbridges);
+struct amd_northbridge_info amd_northbridges;
+EXPORT_SYMBOL(amd_northbridges);
 
-static struct pci_dev *next_k8_northbridge(struct pci_dev *dev)
+static struct pci_dev *next_northbridge(struct pci_dev *dev,
+					struct pci_device_id *ids)
 {
 	do {
 		dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
 		if (!dev)
 			break;
-	} while (!pci_match_id(&k8_nb_ids[0], dev));
+	} while (!pci_match_id(ids, dev));
 	return dev;
 }
 
-int cache_k8_northbridges(void)
+int amd_cache_northbridges(void)
 {
-	int i;
-	struct pci_dev *dev;
+	int i = 0;
+	struct amd_northbridge *nb;
+	struct pci_dev *misc;
 
-	if (k8_northbridges.num)
+	if (amd_nb_num())
 		return 0;
 
-	dev = NULL;
-	while ((dev = next_k8_northbridge(dev)) != NULL)
-		k8_northbridges.num++;
+	misc = NULL;
+	while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
+		i++;
 
-	/* some CPU families (e.g. family 0x11) do not support GART */
-	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
-	    boot_cpu_data.x86 == 0x15)
-		k8_northbridges.gart_supported = 1;
+	if (i == 0)
+		return 0;
 
-	k8_northbridges.nb_misc = kmalloc((k8_northbridges.num + 1) *
-					  sizeof(void *), GFP_KERNEL);
-	if (!k8_northbridges.nb_misc)
+	nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL);
+	if (!nb)
 		return -ENOMEM;
 
-	if (!k8_northbridges.num) {
-		k8_northbridges.nb_misc[0] = NULL;
-		return 0;
-	}
+	amd_northbridges.nb = nb;
+	amd_northbridges.num = i;
 
-	if (k8_northbridges.gart_supported) {
-		flush_words = kmalloc(k8_northbridges.num * sizeof(u32),
-				      GFP_KERNEL);
-		if (!flush_words) {
-			kfree(k8_northbridges.nb_misc);
-			return -ENOMEM;
-		}
-	}
+	misc = NULL;
+	for (i = 0; i != amd_nb_num(); i++) {
+		node_to_amd_nb(i)->misc = misc =
+			next_northbridge(misc, amd_nb_misc_ids);
+        }
+
+	/* some CPU families (e.g. family 0x11) do not support GART */
+	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
+	    boot_cpu_data.x86 == 0x15)
+		amd_northbridges.flags |= AMD_NB_GART;
+
+	/*
+	 * Some CPU families support L3 Cache Index Disable. There are some
+	 * limitations because of E382 and E388 on family 0x10.
+	 */
+	if (boot_cpu_data.x86 == 0x10 &&
+	    boot_cpu_data.x86_model >= 0x8 &&
+	    (boot_cpu_data.x86_model > 0x9 ||
+	     boot_cpu_data.x86_mask >= 0x1))
+		amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE;
 
-	dev = NULL;
-	i = 0;
-	while ((dev = next_k8_northbridge(dev)) != NULL) {
-		k8_northbridges.nb_misc[i] = dev;
-		if (k8_northbridges.gart_supported)
-			pci_read_config_dword(dev, 0x9c, &flush_words[i++]);
-	}
-	k8_northbridges.nb_misc[i] = NULL;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cache_k8_northbridges);
+EXPORT_SYMBOL_GPL(amd_cache_northbridges);
 
 /* Ignores subdevice/subvendor but as far as I can figure out
    they're useless anyways */
-int __init early_is_k8_nb(u32 device)
+int __init early_is_amd_nb(u32 device)
 {
 	struct pci_device_id *id;
 	u32 vendor = device & 0xffff;
 	device >>= 16;
-	for (id = k8_nb_ids; id->vendor; id++)
+	for (id = amd_nb_misc_ids; id->vendor; id++)
 		if (vendor == id->vendor && device == id->device)
 			return 1;
 	return 0;
 }
 
-void k8_flush_garts(void)
+int amd_cache_gart(void)
+{
+       int i;
+
+       if (!amd_nb_has_feature(AMD_NB_GART))
+               return 0;
+
+       flush_words = kmalloc(amd_nb_num() * sizeof(u32), GFP_KERNEL);
+       if (!flush_words) {
+               amd_northbridges.flags &= ~AMD_NB_GART;
+               return -ENOMEM;
+       }
+
+       for (i = 0; i != amd_nb_num(); i++)
+               pci_read_config_dword(node_to_amd_nb(i)->misc, 0x9c,
+                                     &flush_words[i]);
+
+       return 0;
+}
+
+void amd_flush_garts(void)
 {
 	int flushed, i;
 	unsigned long flags;
 	static DEFINE_SPINLOCK(gart_lock);
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return;
 
 	/* Avoid races between AGP and IOMMU. In theory it's not needed
@@ -109,16 +130,16 @@ void k8_flush_garts(void)
 	   that it doesn't matter to serialize more. -AK */
 	spin_lock_irqsave(&gart_lock, flags);
 	flushed = 0;
-	for (i = 0; i < k8_northbridges.num; i++) {
-		pci_write_config_dword(k8_northbridges.nb_misc[i], 0x9c,
-				       flush_words[i]|1);
+	for (i = 0; i < amd_nb_num(); i++) {
+		pci_write_config_dword(node_to_amd_nb(i)->misc, 0x9c,
+				       flush_words[i] | 1);
 		flushed++;
 	}
-	for (i = 0; i < k8_northbridges.num; i++) {
+	for (i = 0; i < amd_nb_num(); i++) {
 		u32 w;
 		/* Make sure the hardware actually executed the flush*/
 		for (;;) {
-			pci_read_config_dword(k8_northbridges.nb_misc[i],
+			pci_read_config_dword(node_to_amd_nb(i)->misc,
 					      0x9c, &w);
 			if (!(w & 1))
 				break;
@@ -129,19 +150,23 @@ void k8_flush_garts(void)
 	if (!flushed)
 		printk("nothing to flush?\n");
 }
-EXPORT_SYMBOL_GPL(k8_flush_garts);
+EXPORT_SYMBOL_GPL(amd_flush_garts);
 
-static __init int init_k8_nbs(void)
+static __init int init_amd_nbs(void)
 {
 	int err = 0;
 
-	err = cache_k8_northbridges();
+	err = amd_cache_northbridges();
 
 	if (err < 0)
-		printk(KERN_NOTICE "K8 NB: Cannot enumerate AMD northbridges.\n");
+		printk(KERN_NOTICE "AMD NB: Cannot enumerate AMD northbridges.\n");
+
+	if (amd_cache_gart() < 0)
+		printk(KERN_NOTICE "AMD NB: Cannot initialize GART flush words, "
+		       "GART support disabled.\n");
 
 	return err;
 }
 
 /* This has to go after the PCI subsystem */
-fs_initcall(init_k8_nbs);
+fs_initcall(init_amd_nbs);

arch/x86/kernel/apb_timer.c

@@ -315,6 +315,7 @@ static void apbt_setup_irq(struct apbt_dev *adev)
 
 	if (system_state == SYSTEM_BOOTING) {
 		irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
+		irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
 		/* APB timer irqs are set up as mp_irqs, timer is edge type */
 		__set_irq_handler(adev->irq, handle_edge_irq, 0, "edge");
 		if (request_irq(adev->irq, apbt_interrupt_handler,

arch/x86/kernel/aperture_64.c

@@ -206,7 +206,7 @@ static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
  * Do an PCI bus scan by hand because we're running before the PCI
  * subsystem.
  *
- * All K8 AGP bridges are AGPv3 compliant, so we can do this scan
+ * All AMD AGP bridges are AGPv3 compliant, so we can do this scan
  * generically. It's probably overkill to always scan all slots because
  * the AGP bridges should be always an own bus on the HT hierarchy,
  * but do it here for future safety.
@@ -303,7 +303,7 @@ void __init early_gart_iommu_check(void)
 		dev_limit = bus_dev_ranges[i].dev_limit;
 
 		for (slot = dev_base; slot < dev_limit; slot++) {
-			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+			if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
 				continue;
 
 			ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
@@ -358,7 +358,7 @@ void __init early_gart_iommu_check(void)
 		dev_limit = bus_dev_ranges[i].dev_limit;
 
 		for (slot = dev_base; slot < dev_limit; slot++) {
-			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+			if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
 				continue;
 
 			ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
@@ -400,7 +400,7 @@ int __init gart_iommu_hole_init(void)
 		dev_limit = bus_dev_ranges[i].dev_limit;
 
 		for (slot = dev_base; slot < dev_limit; slot++) {
-			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+			if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
 				continue;
 
 			iommu_detected = 1;
@@ -518,7 +518,7 @@ out:
 		dev_base = bus_dev_ranges[i].dev_base;
 		dev_limit = bus_dev_ranges[i].dev_limit;
 		for (slot = dev_base; slot < dev_limit; slot++) {
-			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+			if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
 				continue;
 
 			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);

arch/x86/kernel/apic/apic.c

@@ -431,17 +431,18 @@ int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
 	reserved = reserve_eilvt_offset(offset, new);
 
 	if (reserved != new) {
-		pr_err(FW_BUG "cpu %d, try to setup vector 0x%x, but "
-		       "vector 0x%x was already reserved by another core, "
-		       "APIC%lX=0x%x\n",
-		       smp_processor_id(), new, reserved, reg, old);
+		pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for "
+		       "vector 0x%x, but the register is already in use for "
+		       "vector 0x%x on another cpu\n",
+		       smp_processor_id(), reg, offset, new, reserved);
 		return -EINVAL;
 	}
 
 	if (!eilvt_entry_is_changeable(old, new)) {
-		pr_err(FW_BUG "cpu %d, try to setup vector 0x%x but "
-		       "register already in use, APIC%lX=0x%x\n",
-		       smp_processor_id(), new, reg, old);
+		pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for "
+		       "vector 0x%x, but the register is already in use for "
+		       "vector 0x%x on this cpu\n",
+		       smp_processor_id(), reg, offset, new, old);
 		return -EBUSY;
 	}
 
@@ -1532,13 +1533,60 @@ static int __init detect_init_APIC(void)
 	return 0;
 }
 #else
+
+static int apic_verify(void)
+{
+	u32 features, h, l;
+
+	/*
+	 * The APIC feature bit should now be enabled
+	 * in `cpuid'
+	 */
+	features = cpuid_edx(1);
+	if (!(features & (1 << X86_FEATURE_APIC))) {
+		pr_warning("Could not enable APIC!\n");
+		return -1;
+	}
+	set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
+	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
+
+	/* The BIOS may have set up the APIC at some other address */
+	rdmsr(MSR_IA32_APICBASE, l, h);
+	if (l & MSR_IA32_APICBASE_ENABLE)
+		mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
+
+	pr_info("Found and enabled local APIC!\n");
+	return 0;
+}
+
+int apic_force_enable(void)
+{
+	u32 h, l;
+
+	if (disable_apic)
+		return -1;
+
+	/*
+	 * Some BIOSes disable the local APIC in the APIC_BASE
+	 * MSR. This can only be done in software for Intel P6 or later
+	 * and AMD K7 (Model > 1) or later.
+	 */
+	rdmsr(MSR_IA32_APICBASE, l, h);
+	if (!(l & MSR_IA32_APICBASE_ENABLE)) {
+		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);
+		enabled_via_apicbase = 1;
+	}
+	return apic_verify();
+}
+
 /*
  * Detect and initialize APIC
  */
 static int __init detect_init_APIC(void)
 {
-	u32 h, l, features;
-
 	/* Disabled by kernel option? */
 	if (disable_apic)
 		return -1;
@@ -1568,38 +1616,12 @@ static int __init detect_init_APIC(void)
 				"you can enable it with \"lapic\"\n");
 			return -1;
 		}
-		/*
-		 * Some BIOSes disable the local APIC in the APIC_BASE
-		 * MSR. This can only be done in software for Intel P6 or later
-		 * and AMD K7 (Model > 1) or later.
-		 */
-		rdmsr(MSR_IA32_APICBASE, l, h);
-		if (!(l & MSR_IA32_APICBASE_ENABLE)) {
-			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);
-			enabled_via_apicbase = 1;
-		}
-	}
-	/*
-	 * The APIC feature bit should now be enabled
-	 * in `cpuid'
-	 */
-	features = cpuid_edx(1);
-	if (!(features & (1 << X86_FEATURE_APIC))) {
-		pr_warning("Could not enable APIC!\n");
-		return -1;
+		if (apic_force_enable())
+			return -1;
+	} else {
+		if (apic_verify())
+			return -1;
 	}
-	set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
-	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
-
-	/* The BIOS may have set up the APIC at some other address */
-	rdmsr(MSR_IA32_APICBASE, l, h);
-	if (l & MSR_IA32_APICBASE_ENABLE)
-		mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
-
-	pr_info("Found and enabled local APIC!\n");
 
 	apic_pm_activate();
 
@@ -1687,7 +1709,7 @@ void __init init_apic_mappings(void)
  * This initializes the IO-APIC and APIC hardware if this is
  * a UP kernel.
  */
-int apic_version[MAX_APICS];
+int apic_version[MAX_LOCAL_APIC];
 
 int __init APIC_init_uniprocessor(void)
 {

arch/x86/kernel/apic/io_apic.c

@@ -1933,8 +1933,7 @@ void disable_IO_APIC(void)
  *
  * by Matt Domsch <Matt_Domsch@dell.com>  Tue Dec 21 12:25:05 CST 1999
  */
-
-void __init setup_ioapic_ids_from_mpc(void)
+void __init setup_ioapic_ids_from_mpc_nocheck(void)
 {
 	union IO_APIC_reg_00 reg_00;
 	physid_mask_t phys_id_present_map;
@@ -1943,15 +1942,6 @@ void __init setup_ioapic_ids_from_mpc(void)
 	unsigned char old_id;
 	unsigned long flags;
 
-	if (acpi_ioapic)
-		return;
-	/*
-	 * Don't check I/O APIC IDs for xAPIC systems.  They have
-	 * no meaning without the serial APIC bus.
-	 */
-	if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
-		|| APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
-		return;
 	/*
 	 * This is broken; anything with a real cpu count has to
 	 * circumvent this idiocy regardless.
@@ -2005,7 +1995,6 @@ void __init setup_ioapic_ids_from_mpc(void)
 			physids_or(phys_id_present_map, phys_id_present_map, tmp);
 		}
 
-
 		/*
 		 * We need to adjust the IRQ routing table
 		 * if the ID changed.
@@ -2041,6 +2030,21 @@ void __init setup_ioapic_ids_from_mpc(void)
 			apic_printk(APIC_VERBOSE, " ok.\n");
 	}
 }
+
+void __init setup_ioapic_ids_from_mpc(void)
+{
+
+	if (acpi_ioapic)
+		return;
+	/*
+	 * Don't check I/O APIC IDs for xAPIC systems.  They have
+	 * no meaning without the serial APIC bus.
+	 */
+	if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		|| APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+		return;
+	setup_ioapic_ids_from_mpc_nocheck();
+}
 #endif
 
 int no_timer_check __initdata;
@@ -3593,7 +3597,7 @@ int __init io_apic_get_redir_entries (int ioapic)
 	return reg_01.bits.entries + 1;
 }
 
-void __init probe_nr_irqs_gsi(void)
+static void __init probe_nr_irqs_gsi(void)
 {
 	int nr;
 
@@ -3910,7 +3914,7 @@ static struct resource * __init ioapic_setup_resources(int nr_ioapics)
 	return res;
 }
 
-void __init ioapic_init_mappings(void)
+void __init ioapic_and_gsi_init(void)
 {
 	unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
 	struct resource *ioapic_res;
@@ -3948,6 +3952,8 @@ fake_ioapic_page:
 		ioapic_res->end = ioapic_phys + IO_APIC_SLOT_SIZE - 1;
 		ioapic_res++;
 	}
+
+	probe_nr_irqs_gsi();
 }
 
 void __init ioapic_insert_resources(void)
@@ -4057,7 +4063,8 @@ void __init pre_init_apic_IRQ0(void)
 
 	printk(KERN_INFO "Early APIC setup for system timer0\n");
 #ifndef CONFIG_SMP
-	phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
+	physid_set_mask_of_physid(boot_cpu_physical_apicid,
+					 &phys_cpu_present_map);
 #endif
 	/* Make sure the irq descriptor is set up */
 	cfg = alloc_irq_and_cfg_at(0, 0);

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -48,6 +48,16 @@ unsigned int uv_apicid_hibits;
 EXPORT_SYMBOL_GPL(uv_apicid_hibits);
 static DEFINE_SPINLOCK(uv_nmi_lock);
 
+static unsigned long __init uv_early_read_mmr(unsigned long addr)
+{
+	unsigned long val, *mmr;
+
+	mmr = early_ioremap(UV_LOCAL_MMR_BASE | addr, sizeof(*mmr));
+	val = *mmr;
+	early_iounmap(mmr, sizeof(*mmr));
+	return val;
+}
+
 static inline bool is_GRU_range(u64 start, u64 end)
 {
 	return start >= gru_start_paddr && end <= gru_end_paddr;
@@ -58,28 +68,24 @@ static bool uv_is_untracked_pat_range(u64 start, u64 end)
 	return is_ISA_range(start, end) || is_GRU_range(start, end);
 }
 
-static int early_get_nodeid(void)
+static int __init early_get_pnodeid(void)
 {
 	union uvh_node_id_u node_id;
-	unsigned long *mmr;
-
-	mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr));
-	node_id.v = *mmr;
-	early_iounmap(mmr, sizeof(*mmr));
+	union uvh_rh_gam_config_mmr_u  m_n_config;
+	int pnode;
 
 	/* Currently, all blades have same revision number */
+	node_id.v = uv_early_read_mmr(UVH_NODE_ID);
+	m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_CONFIG_MMR);
 	uv_min_hub_revision_id = node_id.s.revision;
 
-	return node_id.s.node_id;
+	pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1);
+	return pnode;
 }
 
 static void __init early_get_apic_pnode_shift(void)
 {
-	unsigned long *mmr;
-
-	mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_APICID, sizeof(*mmr));
-	uvh_apicid.v = *mmr;
-	early_iounmap(mmr, sizeof(*mmr));
+	uvh_apicid.v = uv_early_read_mmr(UVH_APICID);
 	if (!uvh_apicid.v)
 		/*
 		 * Old bios, use default value
@@ -95,21 +101,17 @@ static void __init early_get_apic_pnode_shift(void)
 static void __init uv_set_apicid_hibit(void)
 {
 	union uvh_lb_target_physical_apic_id_mask_u apicid_mask;
-	unsigned long *mmr;
 
-	mmr = early_ioremap(UV_LOCAL_MMR_BASE |
-		UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK, sizeof(*mmr));
-	apicid_mask.v = *mmr;
-	early_iounmap(mmr, sizeof(*mmr));
+	apicid_mask.v = uv_early_read_mmr(UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK);
 	uv_apicid_hibits = apicid_mask.s.bit_enables & UV_APICID_HIBIT_MASK;
 }
 
 static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
-	int nodeid;
+	int pnodeid;
 
 	if (!strcmp(oem_id, "SGI")) {
-		nodeid = early_get_nodeid();
+		pnodeid = early_get_pnodeid();
 		early_get_apic_pnode_shift();
 		x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
 		x86_platform.nmi_init = uv_nmi_init;
@@ -119,7 +121,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 			uv_system_type = UV_X2APIC;
 		else if (!strcmp(oem_table_id, "UVH")) {
 			__get_cpu_var(x2apic_extra_bits) =
-				nodeid << (uvh_apicid.s.pnode_shift - 1);
+				pnodeid << uvh_apicid.s.pnode_shift;
 			uv_system_type = UV_NON_UNIQUE_APIC;
 			uv_set_apicid_hibit();
 			return 1;
@@ -682,27 +684,32 @@ void uv_nmi_init(void)
 void __init uv_system_init(void)
 {
 	union uvh_rh_gam_config_mmr_u  m_n_config;
+	union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh;
 	union uvh_node_id_u node_id;
 	unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
-	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
+	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val, n_io;
 	int gnode_extra, max_pnode = 0;
 	unsigned long mmr_base, present, paddr;
-	unsigned short pnode_mask;
+	unsigned short pnode_mask, pnode_io_mask;
 
 	map_low_mmrs();
 
 	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
 	m_val = m_n_config.s.m_skt;
 	n_val = m_n_config.s.n_skt;
+	mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
+	n_io = mmioh.s.n_io;
 	mmr_base =
 	    uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
 	    ~UV_MMR_ENABLE;
 	pnode_mask = (1 << n_val) - 1;
+	pnode_io_mask = (1 << n_io) - 1;
+
 	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
 	gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1;
 	gnode_upper = ((unsigned long)gnode_extra  << m_val);
-	printk(KERN_DEBUG "UV: N %d, M %d, gnode_upper 0x%lx, gnode_extra 0x%x\n",
-			n_val, m_val, gnode_upper, gnode_extra);
+	printk(KERN_INFO "UV: N %d, M %d, N_IO: %d, gnode_upper 0x%lx, gnode_extra 0x%x, pnode_mask 0x%x, pnode_io_mask 0x%x\n",
+			n_val, m_val, n_io, gnode_upper, gnode_extra, pnode_mask, pnode_io_mask);
 
 	printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base);
 
@@ -735,7 +742,7 @@ void __init uv_system_init(void)
 		for (j = 0; j < 64; j++) {
 			if (!test_bit(j, &present))
 				continue;
-			pnode = (i * 64 + j);
+			pnode = (i * 64 + j) & pnode_mask;
 			uv_blade_info[blade].pnode = pnode;
 			uv_blade_info[blade].nr_possible_cpus = 0;
 			uv_blade_info[blade].nr_online_cpus = 0;
@@ -756,6 +763,7 @@ void __init uv_system_init(void)
 		/*
 		 * apic_pnode_shift must be set before calling uv_apicid_to_pnode();
 		 */
+		uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
 		uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift;
 		pnode = uv_apicid_to_pnode(apicid);
 		blade = boot_pnode_to_blade(pnode);
@@ -772,7 +780,6 @@ void __init uv_system_init(void)
 		uv_cpu_hub_info(cpu)->numa_blade_id = blade;
 		uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
 		uv_cpu_hub_info(cpu)->pnode = pnode;
-		uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
 		uv_cpu_hub_info(cpu)->gpa_mask = (1UL << (m_val + n_val)) - 1;
 		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
 		uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
@@ -796,7 +803,7 @@ void __init uv_system_init(void)
 
 	map_gru_high(max_pnode);
 	map_mmr_high(max_pnode);
-	map_mmioh_high(max_pnode);
+	map_mmioh_high(max_pnode & pnode_io_mask);
 
 	uv_cpu_init();
 	uv_scir_register_cpu_notifier();

arch/x86/kernel/cpu/intel_cacheinfo.c

@@ -149,8 +149,7 @@ union _cpuid4_leaf_ecx {
 };
 
 struct amd_l3_cache {
-	struct	 pci_dev *dev;
-	bool	 can_disable;
+	struct	 amd_northbridge *nb;
 	unsigned indices;
 	u8	 subcaches[4];
 };
@@ -311,14 +310,12 @@ struct _cache_attr {
 /*
  * L3 cache descriptors
  */
-static struct amd_l3_cache **__cpuinitdata l3_caches;
-
 static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
 {
 	unsigned int sc0, sc1, sc2, sc3;
 	u32 val = 0;
 
-	pci_read_config_dword(l3->dev, 0x1C4, &val);
+	pci_read_config_dword(l3->nb->misc, 0x1C4, &val);
 
 	/* calculate subcache sizes */
 	l3->subcaches[0] = sc0 = !(val & BIT(0));
@@ -330,47 +327,14 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
 	l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
 }
 
-static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node)
-{
-	struct amd_l3_cache *l3;
-	struct pci_dev *dev = node_to_k8_nb_misc(node);
-
-	l3 = kzalloc(sizeof(struct amd_l3_cache), GFP_ATOMIC);
-	if (!l3) {
-		printk(KERN_WARNING "Error allocating L3 struct\n");
-		return NULL;
-	}
-
-	l3->dev = dev;
-
-	amd_calc_l3_indices(l3);
-
-	return l3;
-}
-
-static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
-					   int index)
+static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf,
+					int index)
 {
+	static struct amd_l3_cache *__cpuinitdata l3_caches;
 	int node;
 
-	if (boot_cpu_data.x86 != 0x10)
-		return;
-
-	if (index < 3)
-		return;
-
-	/* see errata #382 and #388 */
-	if (boot_cpu_data.x86_model < 0x8)
-		return;
-
-	if ((boot_cpu_data.x86_model == 0x8 ||
-	     boot_cpu_data.x86_model == 0x9)
-		&&
-	     boot_cpu_data.x86_mask < 0x1)
-			return;
-
-	/* not in virtualized environments */
-	if (k8_northbridges.num == 0)
+	/* only for L3, and not in virtualized environments */
+	if (index < 3 || amd_nb_num() == 0)
 		return;
 
 	/*
@@ -378,7 +342,7 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
 	 * never freed but this is done only on shutdown so it doesn't matter.
 	 */
 	if (!l3_caches) {
-		int size = k8_northbridges.num * sizeof(struct amd_l3_cache *);
+		int size = amd_nb_num() * sizeof(struct amd_l3_cache);
 
 		l3_caches = kzalloc(size, GFP_ATOMIC);
 		if (!l3_caches)
@@ -387,14 +351,12 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
 
 	node = amd_get_nb_id(smp_processor_id());
 
-	if (!l3_caches[node]) {
-		l3_caches[node] = amd_init_l3_cache(node);
-		l3_caches[node]->can_disable = true;
+	if (!l3_caches[node].nb) {
+		l3_caches[node].nb = node_to_amd_nb(node);
+		amd_calc_l3_indices(&l3_caches[node]);
 	}
 
-	WARN_ON(!l3_caches[node]);
-
-	this_leaf->l3 = l3_caches[node];
+	this_leaf->l3 = &l3_caches[node];
 }
 
 /*
@@ -408,7 +370,7 @@ int amd_get_l3_disable_slot(struct amd_l3_cache *l3, unsigned slot)
 {
 	unsigned int reg = 0;
 
-	pci_read_config_dword(l3->dev, 0x1BC + slot * 4, &reg);
+	pci_read_config_dword(l3->nb->misc, 0x1BC + slot * 4, &reg);
 
 	/* check whether this slot is activated already */
 	if (reg & (3UL << 30))
@@ -422,7 +384,8 @@ static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
 {
 	int index;
 
-	if (!this_leaf->l3 || !this_leaf->l3->can_disable)
+	if (!this_leaf->l3 ||
+	    !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
 		return -EINVAL;
 
 	index = amd_get_l3_disable_slot(this_leaf->l3, slot);
@@ -457,7 +420,7 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
 		if (!l3->subcaches[i])
 			continue;
 
-		pci_write_config_dword(l3->dev, 0x1BC + slot * 4, reg);
+		pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg);
 
 		/*
 		 * We need to WBINVD on a core on the node containing the L3
@@ -467,7 +430,7 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
 		wbinvd_on_cpu(cpu);
 
 		reg |= BIT(31);
-		pci_write_config_dword(l3->dev, 0x1BC + slot * 4, reg);
+		pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg);
 	}
 }
 
@@ -524,7 +487,8 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!this_leaf->l3 || !this_leaf->l3->can_disable)
+	if (!this_leaf->l3 ||
+	    !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
 		return -EINVAL;
 
 	cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
@@ -545,7 +509,7 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
 #define STORE_CACHE_DISABLE(slot)					\
 static ssize_t								\
 store_cache_disable_##slot(struct _cpuid4_info *this_leaf,		\
-			    const char *buf, size_t count)		\
+			   const char *buf, size_t count)		\
 {									\
 	return store_cache_disable(this_leaf, buf, count, slot);	\
 }
@@ -558,10 +522,7 @@ static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
 		show_cache_disable_1, store_cache_disable_1);
 
 #else	/* CONFIG_AMD_NB */
-static void __cpuinit
-amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, int index)
-{
-};
+#define amd_init_l3_cache(x, y)
 #endif /* CONFIG_AMD_NB */
 
 static int
@@ -575,7 +536,7 @@ __cpuinit cpuid4_cache_lookup_regs(int index,
 
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
 		amd_cpuid4(index, &eax, &ebx, &ecx);
-		amd_check_l3_disable(this_leaf, index);
+		amd_init_l3_cache(this_leaf, index);
 	} else {
 		cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
 	}
@@ -983,30 +944,48 @@ define_one_ro(size);
 define_one_ro(shared_cpu_map);
 define_one_ro(shared_cpu_list);
 
-#define DEFAULT_SYSFS_CACHE_ATTRS	\
-	&type.attr,			\
-	&level.attr,			\
-	&coherency_line_size.attr,	\
-	&physical_line_partition.attr,	\
-	&ways_of_associativity.attr,	\
-	&number_of_sets.attr,		\
-	&size.attr,			\
-	&shared_cpu_map.attr,		\
-	&shared_cpu_list.attr
-
 static struct attribute *default_attrs[] = {
-	DEFAULT_SYSFS_CACHE_ATTRS,
+	&type.attr,
+	&level.attr,
+	&coherency_line_size.attr,
+	&physical_line_partition.attr,
+	&ways_of_associativity.attr,
+	&number_of_sets.attr,
+	&size.attr,
+	&shared_cpu_map.attr,
+	&shared_cpu_list.attr,
 	NULL
 };
 
-static struct attribute *default_l3_attrs[] = {
-	DEFAULT_SYSFS_CACHE_ATTRS,
 #ifdef CONFIG_AMD_NB
-	&cache_disable_0.attr,
-	&cache_disable_1.attr,
+static struct attribute ** __cpuinit amd_l3_attrs(void)
+{
+	static struct attribute **attrs;
+	int n;
+
+	if (attrs)
+		return attrs;
+
+	n = sizeof (default_attrs) / sizeof (struct attribute *);
+
+	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+		n += 2;
+
+	attrs = kzalloc(n * sizeof (struct attribute *), GFP_KERNEL);
+	if (attrs == NULL)
+		return attrs = default_attrs;
+
+	for (n = 0; default_attrs[n]; n++)
+		attrs[n] = default_attrs[n];
+
+	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) {
+		attrs[n++] = &cache_disable_0.attr;
+		attrs[n++] = &cache_disable_1.attr;
+	}
+
+	return attrs;
+}
 #endif
-	NULL
-};
 
 static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 {
@@ -1117,11 +1096,11 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 
 		this_leaf = CPUID4_INFO_IDX(cpu, i);
 
-		if (this_leaf->l3 && this_leaf->l3->can_disable)
-			ktype_cache.default_attrs = default_l3_attrs;
-		else
-			ktype_cache.default_attrs = default_attrs;
-
+		ktype_cache.default_attrs = default_attrs;
+#ifdef CONFIG_AMD_NB
+		if (this_leaf->l3)
+			ktype_cache.default_attrs = amd_l3_attrs();
+#endif
 		retval = kobject_init_and_add(&(this_object->kobj),
 					      &ktype_cache,
 					      per_cpu(ici_cache_kobject, cpu),

arch/x86/kernel/cpu/mcheck/mce_amd.c

@@ -31,8 +31,6 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 
-#define PFX               "mce_threshold: "
-#define VERSION           "version 1.1.1"
 #define NR_BANKS          6
 #define NR_BLOCKS         9
 #define THRESHOLD_MAX     0xFFF
@@ -59,12 +57,6 @@ struct threshold_block {
 	struct list_head	miscj;
 };
 
-/* defaults used early on boot */
-static struct threshold_block threshold_defaults = {
-	.interrupt_enable	= 0,
-	.threshold_limit	= THRESHOLD_MAX,
-};
-
 struct threshold_bank {
 	struct kobject		*kobj;
 	struct threshold_block	*blocks;
@@ -89,50 +81,101 @@ static void amd_threshold_interrupt(void);
 struct thresh_restart {
 	struct threshold_block	*b;
 	int			reset;
+	int			set_lvt_off;
+	int			lvt_off;
 	u16			old_limit;
 };
 
+static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
+{
+	int msr = (hi & MASK_LVTOFF_HI) >> 20;
+
+	if (apic < 0) {
+		pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt "
+		       "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu,
+		       b->bank, b->block, b->address, hi, lo);
+		return 0;
+	}
+
+	if (apic != msr) {
+		pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d "
+		       "for bank %d, block %d (MSR%08X=0x%x%08x)\n",
+		       b->cpu, apic, b->bank, b->block, b->address, hi, lo);
+		return 0;
+	}
+
+	return 1;
+};
+
 /* must be called with correct cpu affinity */
 /* Called via smp_call_function_single() */
 static void threshold_restart_bank(void *_tr)
 {
 	struct thresh_restart *tr = _tr;
-	u32 mci_misc_hi, mci_misc_lo;
+	u32 hi, lo;
 
-	rdmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
+	rdmsr(tr->b->address, lo, hi);
 
-	if (tr->b->threshold_limit < (mci_misc_hi & THRESHOLD_MAX))
+	if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
 		tr->reset = 1;	/* limit cannot be lower than err count */
 
 	if (tr->reset) {		/* reset err count and overflow bit */
-		mci_misc_hi =
-		    (mci_misc_hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
+		hi =
+		    (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
 		    (THRESHOLD_MAX - tr->b->threshold_limit);
 	} else if (tr->old_limit) {	/* change limit w/o reset */
-		int new_count = (mci_misc_hi & THRESHOLD_MAX) +
+		int new_count = (hi & THRESHOLD_MAX) +
 		    (tr->old_limit - tr->b->threshold_limit);
 
-		mci_misc_hi = (mci_misc_hi & ~MASK_ERR_COUNT_HI) |
+		hi = (hi & ~MASK_ERR_COUNT_HI) |
 		    (new_count & THRESHOLD_MAX);
 	}
 
+	if (tr->set_lvt_off) {
+		if (lvt_off_valid(tr->b, tr->lvt_off, lo, hi)) {
+			/* set new lvt offset */
+			hi &= ~MASK_LVTOFF_HI;
+			hi |= tr->lvt_off << 20;
+		}
+	}
+
 	tr->b->interrupt_enable ?
-	    (mci_misc_hi = (mci_misc_hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
-	    (mci_misc_hi &= ~MASK_INT_TYPE_HI);
+	    (hi = (hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
+	    (hi &= ~MASK_INT_TYPE_HI);
 
-	mci_misc_hi |= MASK_COUNT_EN_HI;
-	wrmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
+	hi |= MASK_COUNT_EN_HI;
+	wrmsr(tr->b->address, lo, hi);
+}
+
+static void mce_threshold_block_init(struct threshold_block *b, int offset)
+{
+	struct thresh_restart tr = {
+		.b			= b,
+		.set_lvt_off		= 1,
+		.lvt_off		= offset,
+	};
+
+	b->threshold_limit		= THRESHOLD_MAX;
+	threshold_restart_bank(&tr);
+};
+
+static int setup_APIC_mce(int reserved, int new)
+{
+	if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
+					      APIC_EILVT_MSG_FIX, 0))
+		return new;
+
+	return reserved;
 }
 
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
+	struct threshold_block b;
 	unsigned int cpu = smp_processor_id();
 	u32 low = 0, high = 0, address = 0;
 	unsigned int bank, block;
-	struct thresh_restart tr;
-	int lvt_off = -1;
-	u8 offset;
+	int offset = -1;
 
 	for (bank = 0; bank < NR_BANKS; ++bank) {
 		for (block = 0; block < NR_BLOCKS; ++block) {
@@ -163,39 +206,16 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 			if (shared_bank[bank] && c->cpu_core_id)
 				break;
 #endif
-			offset = (high & MASK_LVTOFF_HI) >> 20;
-			if (lvt_off < 0) {
-				if (setup_APIC_eilvt(offset,
-						     THRESHOLD_APIC_VECTOR,
-						     APIC_EILVT_MSG_FIX, 0)) {
-					pr_err(FW_BUG "cpu %d, failed to "
-					       "setup threshold interrupt "
-					       "for bank %d, block %d "
-					       "(MSR%08X=0x%x%08x)",
-					       smp_processor_id(), bank, block,
-					       address, high, low);
-					continue;
-				}
-				lvt_off = offset;
-			} else if (lvt_off != offset) {
-				pr_err(FW_BUG "cpu %d, invalid threshold "
-				       "interrupt offset %d for bank %d,"
-				       "block %d (MSR%08X=0x%x%08x)",
-				       smp_processor_id(), lvt_off, bank,
-				       block, address, high, low);
-				continue;
-			}
-
-			high &= ~MASK_LVTOFF_HI;
-			high |= lvt_off << 20;
-			wrmsr(address, low, high);
+			offset = setup_APIC_mce(offset,
+						(high & MASK_LVTOFF_HI) >> 20);
 
-			threshold_defaults.address = address;
-			tr.b = &threshold_defaults;
-			tr.reset = 0;
-			tr.old_limit = 0;
-			threshold_restart_bank(&tr);
+			memset(&b, 0, sizeof(b));
+			b.cpu		= cpu;
+			b.bank		= bank;
+			b.block		= block;
+			b.address	= address;
 
+			mce_threshold_block_init(&b, offset);
 			mce_threshold_vector = amd_threshold_interrupt;
 		}
 	}
@@ -298,9 +318,8 @@ store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size)
 
 	b->interrupt_enable = !!new;
 
+	memset(&tr, 0, sizeof(tr));
 	tr.b		= b;
-	tr.reset	= 0;
-	tr.old_limit	= 0;
 
 	smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
 
@@ -321,10 +340,10 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size)
 	if (new < 1)
 		new = 1;
 
+	memset(&tr, 0, sizeof(tr));
 	tr.old_limit = b->threshold_limit;
 	b->threshold_limit = new;
 	tr.b = b;
-	tr.reset = 0;
 
 	smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
 
@@ -603,9 +622,9 @@ static __cpuinit int threshold_create_device(unsigned int cpu)
 			continue;
 		err = threshold_create_bank(cpu, bank);
 		if (err)
-			goto out;
+			return err;
 	}
-out:
+
 	return err;
 }
 

arch/x86/kernel/cpu/mcheck/therm_throt.c

@@ -53,8 +53,13 @@ struct thermal_state {
 	struct _thermal_state core_power_limit;
 	struct _thermal_state package_throttle;
 	struct _thermal_state package_power_limit;
+	struct _thermal_state core_thresh0;
+	struct _thermal_state core_thresh1;
 };
 
+/* Callback to handle core threshold interrupts */
+int (*platform_thermal_notify)(__u64 msr_val);
+
 static DEFINE_PER_CPU(struct thermal_state, thermal_state);
 
 static atomic_t therm_throt_en	= ATOMIC_INIT(0);
@@ -200,6 +205,22 @@ static int therm_throt_process(bool new_event, int event, int level)
 	return 0;
 }
 
+static int thresh_event_valid(int event)
+{
+	struct _thermal_state *state;
+	unsigned int this_cpu = smp_processor_id();
+	struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu);
+	u64 now = get_jiffies_64();
+
+	state = (event == 0) ? &pstate->core_thresh0 : &pstate->core_thresh1;
+
+	if (time_before64(now, state->next_check))
+		return 0;
+
+	state->next_check = now + CHECK_INTERVAL;
+	return 1;
+}
+
 #ifdef CONFIG_SYSFS
 /* Add/Remove thermal_throttle interface for CPU device: */
 static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
@@ -313,6 +334,22 @@ device_initcall(thermal_throttle_init_device);
 #define PACKAGE_THROTTLED	((__u64)2 << 62)
 #define PACKAGE_POWER_LIMIT	((__u64)3 << 62)
 
+static void notify_thresholds(__u64 msr_val)
+{
+	/* check whether the interrupt handler is defined;
+	 * otherwise simply return
+	 */
+	if (!platform_thermal_notify)
+		return;
+
+	/* lower threshold reached */
+	if ((msr_val & THERM_LOG_THRESHOLD0) &&	thresh_event_valid(0))
+		platform_thermal_notify(msr_val);
+	/* higher threshold reached */
+	if ((msr_val & THERM_LOG_THRESHOLD1) && thresh_event_valid(1))
+		platform_thermal_notify(msr_val);
+}
+
 /* Thermal transition interrupt handler */
 static void intel_thermal_interrupt(void)
 {
@@ -321,6 +358,9 @@ static void intel_thermal_interrupt(void)
 
 	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
 
+	/* Check for violation of core thermal thresholds*/
+	notify_thresholds(msr_val);
+
 	if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
 				THERMAL_THROTTLING_EVENT,
 				CORE_LEVEL) != 0)

arch/x86/kernel/early_printk.c

@@ -240,7 +240,7 @@ static int __init setup_early_printk(char *buf)
 		if (!strncmp(buf, "xen", 3))
 			early_console_register(&xenboot_console, keep);
 #endif
-#ifdef CONFIG_X86_MRST_EARLY_PRINTK
+#ifdef CONFIG_EARLY_PRINTK_MRST
 		if (!strncmp(buf, "mrst", 4)) {
 			mrst_early_console_init();
 			early_console_register(&early_mrst_console, keep);
@@ -250,7 +250,6 @@ static int __init setup_early_printk(char *buf)
 			hsu_early_console_init();
 			early_console_register(&early_hsu_console, keep);
 		}
-
 #endif
 		buf++;
 	}

arch/x86/kernel/ftrace.c

@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/list.h>
+#include <linux/module.h>
 
 #include <trace/syscall.h>
 
@@ -49,6 +50,7 @@ static DEFINE_PER_CPU(int, save_modifying_code);
 int ftrace_arch_code_modify_prepare(void)
 {
 	set_kernel_text_rw();
+	set_all_modules_text_rw();
 	modifying_code = 1;
 	return 0;
 }
@@ -56,6 +58,7 @@ int ftrace_arch_code_modify_prepare(void)
 int ftrace_arch_code_modify_post_process(void)
 {
 	modifying_code = 0;
+	set_all_modules_text_ro();
 	set_kernel_text_ro();
 	return 0;
 }

arch/x86/kernel/head32.c

@@ -61,6 +61,9 @@ void __init i386_start_kernel(void)
 	case X86_SUBARCH_MRST:
 		x86_mrst_early_setup();
 		break;
+	case X86_SUBARCH_CE4100:
+		x86_ce4100_early_setup();
+		break;
 	default:
 		i386_default_early_setup();
 		break;

arch/x86/kernel/head_32.S

@@ -139,39 +139,6 @@ ENTRY(startup_32)
 	movl %eax, pa(olpc_ofw_pgd)
 #endif
 
-#ifdef CONFIG_PARAVIRT
-	/* This is can only trip for a broken bootloader... */
-	cmpw $0x207, pa(boot_params + BP_version)
-	jb default_entry
-
-	/* Paravirt-compatible boot parameters.  Look to see what architecture
-		we're booting under. */
-	movl pa(boot_params + BP_hardware_subarch), %eax
-	cmpl $num_subarch_entries, %eax
-	jae bad_subarch
-
-	movl pa(subarch_entries)(,%eax,4), %eax
-	subl $__PAGE_OFFSET, %eax
-	jmp *%eax
-
-bad_subarch:
-WEAK(lguest_entry)
-WEAK(xen_entry)
-	/* Unknown implementation; there's really
-	   nothing we can do at this point. */
-	ud2a
-
-	__INITDATA
-
-subarch_entries:
-	.long default_entry		/* normal x86/PC */
-	.long lguest_entry		/* lguest hypervisor */
-	.long xen_entry			/* Xen hypervisor */
-	.long default_entry		/* Moorestown MID */
-num_subarch_entries = (. - subarch_entries) / 4
-.previous
-#endif /* CONFIG_PARAVIRT */
-
 /*
  * Initialize page tables.  This creates a PDE and a set of page
  * tables, which are located immediately beyond __brk_base.  The variable
@@ -181,7 +148,6 @@ num_subarch_entries = (. - subarch_entries) / 4
  *
  * Note that the stack is not yet set up!
  */
-default_entry:
 #ifdef CONFIG_X86_PAE
 
 	/*
@@ -261,7 +227,42 @@ page_pde_offset = (__PAGE_OFFSET >> 20);
 	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
 	movl %eax,pa(initial_page_table+0xffc)
 #endif
-	jmp 3f
+
+#ifdef CONFIG_PARAVIRT
+	/* This is can only trip for a broken bootloader... */
+	cmpw $0x207, pa(boot_params + BP_version)
+	jb default_entry
+
+	/* Paravirt-compatible boot parameters.  Look to see what architecture
+		we're booting under. */
+	movl pa(boot_params + BP_hardware_subarch), %eax
+	cmpl $num_subarch_entries, %eax
+	jae bad_subarch
+
+	movl pa(subarch_entries)(,%eax,4), %eax
+	subl $__PAGE_OFFSET, %eax
+	jmp *%eax
+
+bad_subarch:
+WEAK(lguest_entry)
+WEAK(xen_entry)
+	/* Unknown implementation; there's really
+	   nothing we can do at this point. */
+	ud2a
+
+	__INITDATA
+
+subarch_entries:
+	.long default_entry		/* normal x86/PC */
+	.long lguest_entry		/* lguest hypervisor */
+	.long xen_entry			/* Xen hypervisor */
+	.long default_entry		/* Moorestown MID */
+num_subarch_entries = (. - subarch_entries) / 4
+.previous
+#else
+	jmp default_entry
+#endif /* CONFIG_PARAVIRT */
+
 /*
  * Non-boot CPU entry point; entered from trampoline.S
  * We can't lgdt here, because lgdt itself uses a data segment, but
@@ -282,7 +283,7 @@ ENTRY(startup_32_smp)
 	movl %eax,%fs
 	movl %eax,%gs
 #endif /* CONFIG_SMP */
-3:
+default_entry:
 
 /*
  *	New page tables may be in 4Mbyte page mode and may
@@ -316,6 +317,10 @@ ENTRY(startup_32_smp)
 	subl $0x80000001, %eax
 	cmpl $(0x8000ffff-0x80000001), %eax
 	ja 6f
+
+	/* Clear bogus XD_DISABLE bits */
+	call verify_cpu
+
 	mov $0x80000001, %eax
 	cpuid
 	/* Execute Disable bit supported? */
@@ -611,6 +616,8 @@ ignore_int:
 #endif
 	iret
 
+#include "verify_cpu.S"
+
 	__REFDATA
 .align 4
 ENTRY(initial_code)
@@ -622,13 +629,13 @@ ENTRY(initial_code)
 __PAGE_ALIGNED_BSS
 	.align PAGE_SIZE_asm
 #ifdef CONFIG_X86_PAE
-ENTRY(initial_pg_pmd)
+initial_pg_pmd:
 	.fill 1024*KPMDS,4,0
 #else
 ENTRY(initial_page_table)
 	.fill 1024,4,0
 #endif
-ENTRY(initial_pg_fixmap)
+initial_pg_fixmap:
 	.fill 1024,4,0
 ENTRY(empty_zero_page)
 	.fill 4096,1,0

arch/x86/kernel/microcode_amd.c

@@ -155,12 +155,6 @@ static int apply_microcode_amd(int cpu)
 	return 0;
 }
 
-static int get_ucode_data(void *to, const u8 *from, size_t n)
-{
-	memcpy(to, from, n);
-	return 0;
-}
-
 static void *
 get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
 {
@@ -168,8 +162,7 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
 	u8 section_hdr[UCODE_CONTAINER_SECTION_HDR];
 	void *mc;
 
-	if (get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR))
-		return NULL;
+	get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR);
 
 	if (section_hdr[0] != UCODE_UCODE_TYPE) {
 		pr_err("error: invalid type field in container file section header\n");
@@ -183,16 +176,13 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
 		return NULL;
 	}
 
-	mc = vmalloc(UCODE_MAX_SIZE);
-	if (mc) {
-		memset(mc, 0, UCODE_MAX_SIZE);
-		if (get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR,
-				   total_size)) {
-			vfree(mc);
-			mc = NULL;
-		} else
-			*mc_size = total_size + UCODE_CONTAINER_SECTION_HDR;
-	}
+	mc = vzalloc(UCODE_MAX_SIZE);
+	if (!mc)
+		return NULL;
+
+	get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, total_size);
+	*mc_size = total_size + UCODE_CONTAINER_SECTION_HDR;
+
 	return mc;
 }
 
@@ -202,8 +192,7 @@ static int install_equiv_cpu_table(const u8 *buf)
 	unsigned int *buf_pos = (unsigned int *)container_hdr;
 	unsigned long size;
 
-	if (get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE))
-		return 0;
+	get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE);
 
 	size = buf_pos[2];
 
@@ -219,10 +208,7 @@ static int install_equiv_cpu_table(const u8 *buf)
 	}
 
 	buf += UCODE_CONTAINER_HEADER_SIZE;
-	if (get_ucode_data(equiv_cpu_table, buf, size)) {
-		vfree(equiv_cpu_table);
-		return 0;
-	}
+	get_ucode_data(equiv_cpu_table, buf, size);
 
 	return size + UCODE_CONTAINER_HEADER_SIZE; /* add header length */
 }

arch/x86/kernel/pci-gart_64.c

@@ -143,7 +143,7 @@ static void flush_gart(void)
 
 	spin_lock_irqsave(&iommu_bitmap_lock, flags);
 	if (need_flush) {
-		k8_flush_garts();
+		amd_flush_garts();
 		need_flush = false;
 	}
 	spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
@@ -561,17 +561,17 @@ static void enable_gart_translations(void)
 {
 	int i;
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return;
 
-	for (i = 0; i < k8_northbridges.num; i++) {
-		struct pci_dev *dev = k8_northbridges.nb_misc[i];
+	for (i = 0; i < amd_nb_num(); i++) {
+		struct pci_dev *dev = node_to_amd_nb(i)->misc;
 
 		enable_gart_translation(dev, __pa(agp_gatt_table));
 	}
 
 	/* Flush the GART-TLB to remove stale entries */
-	k8_flush_garts();
+	amd_flush_garts();
 }
 
 /*
@@ -596,13 +596,13 @@ static void gart_fixup_northbridges(struct sys_device *dev)
 	if (!fix_up_north_bridges)
 		return;
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return;
 
 	pr_info("PCI-DMA: Restoring GART aperture settings\n");
 
-	for (i = 0; i < k8_northbridges.num; i++) {
-		struct pci_dev *dev = k8_northbridges.nb_misc[i];
+	for (i = 0; i < amd_nb_num(); i++) {
+		struct pci_dev *dev = node_to_amd_nb(i)->misc;
 
 		/*
 		 * Don't enable translations just yet.  That is the next
@@ -644,7 +644,7 @@ static struct sys_device device_gart = {
  * Private Northbridge GATT initialization in case we cannot use the
  * AGP driver for some reason.
  */
-static __init int init_k8_gatt(struct agp_kern_info *info)
+static __init int init_amd_gatt(struct agp_kern_info *info)
 {
 	unsigned aper_size, gatt_size, new_aper_size;
 	unsigned aper_base, new_aper_base;
@@ -656,8 +656,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
 	aper_size = aper_base = info->aper_size = 0;
 	dev = NULL;
-	for (i = 0; i < k8_northbridges.num; i++) {
-		dev = k8_northbridges.nb_misc[i];
+	for (i = 0; i < amd_nb_num(); i++) {
+		dev = node_to_amd_nb(i)->misc;
 		new_aper_base = read_aperture(dev, &new_aper_size);
 		if (!new_aper_base)
 			goto nommu;
@@ -725,13 +725,13 @@ static void gart_iommu_shutdown(void)
 	if (!no_agp)
 		return;
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return;
 
-	for (i = 0; i < k8_northbridges.num; i++) {
+	for (i = 0; i < amd_nb_num(); i++) {
 		u32 ctl;
 
-		dev = k8_northbridges.nb_misc[i];
+		dev = node_to_amd_nb(i)->misc;
 		pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
 
 		ctl &= ~GARTEN;
@@ -749,14 +749,14 @@ int __init gart_iommu_init(void)
 	unsigned long scratch;
 	long i;
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return 0;
 
 #ifndef CONFIG_AGP_AMD64
 	no_agp = 1;
 #else
 	/* Makefile puts PCI initialization via subsys_initcall first. */
-	/* Add other K8 AGP bridge drivers here */
+	/* Add other AMD AGP bridge drivers here */
 	no_agp = no_agp ||
 		(agp_amd64_init() < 0) ||
 		(agp_copy_info(agp_bridge, &info) < 0);
@@ -765,7 +765,7 @@ int __init gart_iommu_init(void)
 	if (no_iommu ||
 	    (!force_iommu && max_pfn <= MAX_DMA32_PFN) ||
 	    !gart_iommu_aperture ||
-	    (no_agp && init_k8_gatt(&info) < 0)) {
+	    (no_agp && init_amd_gatt(&info) < 0)) {
 		if (max_pfn > MAX_DMA32_PFN) {
 			pr_warning("More than 4GB of memory but GART IOMMU not available.\n");
 			pr_warning("falling back to iommu=soft.\n");

arch/x86/kernel/reboot_fixups_32.c

@@ -43,17 +43,33 @@ static void rdc321x_reset(struct pci_dev *dev)
 	outb(1, 0x92);
 }
 
+static void ce4100_reset(struct pci_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < 10; i++) {
+		outb(0x2, 0xcf9);
+		udelay(50);
+	}
+}
+
 struct device_fixup {
 	unsigned int vendor;
 	unsigned int device;
 	void (*reboot_fixup)(struct pci_dev *);
 };
 
+/*
+ * PCI ids solely used for fixups_table go here
+ */
+#define PCI_DEVICE_ID_INTEL_CE4100	0x0708
+
 static const struct device_fixup fixups_table[] = {
 { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, cs5530a_warm_reset },
 { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, cs5536_warm_reset },
 { PCI_VENDOR_ID_NS, PCI_DEVICE_ID_NS_SC1100_BRIDGE, cs5530a_warm_reset },
 { PCI_VENDOR_ID_RDC, PCI_DEVICE_ID_RDC_R6030, rdc321x_reset },
+{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CE4100, ce4100_reset },
 };
 
 /*

arch/x86/kernel/setup.c

@@ -705,7 +705,7 @@ static u64 __init get_max_mapped(void)
 void __init setup_arch(char **cmdline_p)
 {
 	int acpi = 0;
-	int k8 = 0;
+	int amd = 0;
 	unsigned long flags;
 
 #ifdef CONFIG_X86_32
@@ -991,12 +991,12 @@ void __init setup_arch(char **cmdline_p)
 	acpi = acpi_numa_init();
 #endif
 
-#ifdef CONFIG_K8_NUMA
+#ifdef CONFIG_AMD_NUMA
 	if (!acpi)
-		k8 = !k8_numa_init(0, max_pfn);
+		amd = !amd_numa_init(0, max_pfn);
 #endif
 
-	initmem_init(0, max_pfn, acpi, k8);
+	initmem_init(0, max_pfn, acpi, amd);
 	memblock_find_dma_reserve();
 	dma32_reserve_bootmem();
 
@@ -1045,10 +1045,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	init_apic_mappings();
-	ioapic_init_mappings();
-
-	/* need to wait for io_apic is mapped */
-	probe_nr_irqs_gsi();
+	ioapic_and_gsi_init();
 
 	kvm_guest_init();
 

arch/x86/kernel/smpboot.c

@@ -1161,6 +1161,20 @@ out:
 	preempt_enable();
 }
 
+void arch_disable_nonboot_cpus_begin(void)
+{
+	/*
+	 * Avoid the smp alternatives switch during the disable_nonboot_cpus().
+	 * In the suspend path, we will be back in the SMP mode shortly anyways.
+	 */
+	skip_smp_alternatives = true;
+}
+
+void arch_disable_nonboot_cpus_end(void)
+{
+	skip_smp_alternatives = false;
+}
+
 void arch_enable_nonboot_cpus_begin(void)
 {
 	set_mtrr_aps_delayed_init();

arch/x86/kernel/trampoline_64.S

@@ -127,7 +127,7 @@ startup_64:
 no_longmode:
 	hlt
 	jmp no_longmode
-#include "verify_cpu_64.S"
+#include "verify_cpu.S"
 
 	# Careful these need to be in the same 64K segment as the above;
 tidt:

arch/x86/kernel/tsc.c

@@ -872,6 +872,9 @@ __cpuinit int unsynchronized_tsc(void)
 
 	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
 		return 0;
+
+	if (tsc_clocksource_reliable)
+		return 0;
 	/*
 	 * Intel systems are normally all synchronized.
 	 * Exceptions must mark TSC as unstable:
@@ -879,14 +882,92 @@ __cpuinit int unsynchronized_tsc(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
 		/* assume multi socket systems are not synchronized: */
 		if (num_possible_cpus() > 1)
-			tsc_unstable = 1;
+			return 1;
 	}
 
-	return tsc_unstable;
+	return 0;
+}
+
+
+static void tsc_refine_calibration_work(struct work_struct *work);
+static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
+/**
+ * tsc_refine_calibration_work - Further refine tsc freq calibration
+ * @work - ignored.
+ *
+ * This functions uses delayed work over a period of a
+ * second to further refine the TSC freq value. Since this is
+ * timer based, instead of loop based, we don't block the boot
+ * process while this longer calibration is done.
+ *
+ * If there are any calibration anomolies (too many SMIs, etc),
+ * or the refined calibration is off by 1% of the fast early
+ * calibration, we throw out the new calibration and use the
+ * early calibration.
+ */
+static void tsc_refine_calibration_work(struct work_struct *work)
+{
+	static u64 tsc_start = -1, ref_start;
+	static int hpet;
+	u64 tsc_stop, ref_stop, delta;
+	unsigned long freq;
+
+	/* Don't bother refining TSC on unstable systems */
+	if (check_tsc_unstable())
+		goto out;
+
+	/*
+	 * Since the work is started early in boot, we may be
+	 * delayed the first time we expire. So set the workqueue
+	 * again once we know timers are working.
+	 */
+	if (tsc_start == -1) {
+		/*
+		 * Only set hpet once, to avoid mixing hardware
+		 * if the hpet becomes enabled later.
+		 */
+		hpet = is_hpet_enabled();
+		schedule_delayed_work(&tsc_irqwork, HZ);
+		tsc_start = tsc_read_refs(&ref_start, hpet);
+		return;
+	}
+
+	tsc_stop = tsc_read_refs(&ref_stop, hpet);
+
+	/* hpet or pmtimer available ? */
+	if (!hpet && !ref_start && !ref_stop)
+		goto out;
+
+	/* Check, whether the sampling was disturbed by an SMI */
+	if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX)
+		goto out;
+
+	delta = tsc_stop - tsc_start;
+	delta *= 1000000LL;
+	if (hpet)
+		freq = calc_hpet_ref(delta, ref_start, ref_stop);
+	else
+		freq = calc_pmtimer_ref(delta, ref_start, ref_stop);
+
+	/* Make sure we're within 1% */
+	if (abs(tsc_khz - freq) > tsc_khz/100)
+		goto out;
+
+	tsc_khz = freq;
+	printk(KERN_INFO "Refined TSC clocksource calibration: "
+		"%lu.%03lu MHz.\n", (unsigned long)tsc_khz / 1000,
+					(unsigned long)tsc_khz % 1000);
+
+out:
+	clocksource_register_khz(&clocksource_tsc, tsc_khz);
 }
 
-static void __init init_tsc_clocksource(void)
+
+static int __init init_tsc_clocksource(void)
 {
+	if (!cpu_has_tsc || tsc_disabled > 0)
+		return 0;
+
 	if (tsc_clocksource_reliable)
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
 	/* lower the rating if we already know its unstable: */
@@ -894,8 +975,14 @@ static void __init init_tsc_clocksource(void)
 		clocksource_tsc.rating = 0;
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
 	}
-	clocksource_register_khz(&clocksource_tsc, tsc_khz);
+	schedule_delayed_work(&tsc_irqwork, 0);
+	return 0;
 }
+/*
+ * We use device_initcall here, to ensure we run after the hpet
+ * is fully initialized, which may occur at fs_initcall time.
+ */
+device_initcall(init_tsc_clocksource);
 
 void __init tsc_init(void)
 {
@@ -949,6 +1036,5 @@ void __init tsc_init(void)
 		mark_tsc_unstable("TSCs unsynchronized");
 
 	check_system_tsc_reliable();
-	init_tsc_clocksource();
 }
 

arch/x86/kernel/verify_cpu_64.S → arch/x86/kernel/verify_cpu.S

@@ -7,6 +7,7 @@
  *	Copyright (c) 2007  Andi Kleen (ak@suse.de)
  *	Copyright (c) 2007  Eric Biederman (ebiederm@xmission.com)
  *	Copyright (c) 2007  Vivek Goyal (vgoyal@in.ibm.com)
+ *	Copyright (c) 2010  Kees Cook (kees.cook@canonical.com)
  *
  * 	This source code is licensed under the GNU General Public License,
  * 	Version 2.  See the file COPYING for more details.
@@ -14,18 +15,17 @@
  *	This is a common code for verification whether CPU supports
  * 	long mode and SSE or not. It is not called directly instead this
  *	file is included at various places and compiled in that context.
- * 	Following are the current usage.
+ *	This file is expected to run in 32bit code.  Currently:
  *
- * 	This file is included by both 16bit and 32bit code.
+ *	arch/x86/boot/compressed/head_64.S: Boot cpu verification
+ *	arch/x86/kernel/trampoline_64.S: secondary processor verfication
+ *	arch/x86/kernel/head_32.S: processor startup
  *
- *	arch/x86_64/boot/setup.S : Boot cpu verification (16bit)
- *	arch/x86_64/boot/compressed/head.S: Boot cpu verification (32bit)
- *	arch/x86_64/kernel/trampoline.S: secondary processor verfication (16bit)
- *	arch/x86_64/kernel/acpi/wakeup.S:Verfication at resume (16bit)
- *
- *	verify_cpu, returns the status of cpu check in register %eax.
+ *	verify_cpu, returns the status of longmode and SSE in register %eax.
  *		0: Success    1: Failure
  *
+ *	On Intel, the XD_DISABLE flag will be cleared as a side-effect.
+ *
  * 	The caller needs to check for the error code and take the action
  * 	appropriately. Either display a message or halt.
  */
@@ -62,8 +62,41 @@ verify_cpu:
 	cmpl	$0x444d4163,%ecx
 	jnz	verify_cpu_noamd
 	mov	$1,%di			# cpu is from AMD
+	jmp	verify_cpu_check
 
 verify_cpu_noamd:
+	cmpl	$0x756e6547,%ebx        # GenuineIntel?
+	jnz	verify_cpu_check
+	cmpl	$0x49656e69,%edx
+	jnz	verify_cpu_check
+	cmpl	$0x6c65746e,%ecx
+	jnz	verify_cpu_check
+
+	# only call IA32_MISC_ENABLE when:
+	# family > 6 || (family == 6 && model >= 0xd)
+	movl	$0x1, %eax		# check CPU family and model
+	cpuid
+	movl	%eax, %ecx
+
+	andl	$0x0ff00f00, %eax	# mask family and extended family
+	shrl	$8, %eax
+	cmpl	$6, %eax
+	ja	verify_cpu_clear_xd	# family > 6, ok
+	jb	verify_cpu_check	# family < 6, skip
+
+	andl	$0x000f00f0, %ecx	# mask model and extended model
+	shrl	$4, %ecx
+	cmpl	$0xd, %ecx
+	jb	verify_cpu_check	# family == 6, model < 0xd, skip
+
+verify_cpu_clear_xd:
+	movl	$MSR_IA32_MISC_ENABLE, %ecx
+	rdmsr
+	btrl	$2, %edx		# clear MSR_IA32_MISC_ENABLE_XD_DISABLE
+	jnc	verify_cpu_check	# only write MSR if bit was changed
+	wrmsr
+
+verify_cpu_check:
 	movl    $0x1,%eax		# Does the cpu have what it takes
 	cpuid
 	andl	$REQUIRED_MASK0,%edx

arch/x86/kernel/vmlinux.lds.S

@@ -69,7 +69,7 @@ jiffies_64 = jiffies;
 
 PHDRS {
 	text PT_LOAD FLAGS(5);          /* R_E */
-	data PT_LOAD FLAGS(7);          /* RWE */
+	data PT_LOAD FLAGS(6);          /* RW_ */
 #ifdef CONFIG_X86_64
 	user PT_LOAD FLAGS(5);          /* R_E */
 #ifdef CONFIG_SMP
@@ -116,6 +116,10 @@ SECTIONS
 
 	EXCEPTION_TABLE(16) :text = 0x9090
 
+#if defined(CONFIG_DEBUG_RODATA)
+	/* .text should occupy whole number of pages */
+	. = ALIGN(PAGE_SIZE);
+#endif
 	X64_ALIGN_DEBUG_RODATA_BEGIN
 	RO_DATA(PAGE_SIZE)
 	X64_ALIGN_DEBUG_RODATA_END
@@ -335,7 +339,7 @@ SECTIONS
 		__bss_start = .;
 		*(.bss..page_aligned)
 		*(.bss)
-		. = ALIGN(4);
+		. = ALIGN(PAGE_SIZE);
 		__bss_stop = .;
 	}
 

arch/x86/lguest/i386_head.S

@@ -4,7 +4,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/processor-flags.h>
-#include <asm/pgtable.h>
 
 /*G:020
  * Our story starts with the kernel booting into startup_32 in
@@ -38,113 +37,9 @@ ENTRY(lguest_entry)
 	/* Set up the initial stack so we can run C code. */
 	movl $(init_thread_union+THREAD_SIZE),%esp
 
-	call init_pagetables
-
 	/* Jumps are relative: we're running __PAGE_OFFSET too low. */
 	jmp lguest_init+__PAGE_OFFSET
 
-/*
- * Initialize page tables.  This creates a PDE and a set of page
- * tables, which are located immediately beyond __brk_base.  The variable
- * _brk_end is set up to point to the first "safe" location.
- * Mappings are created both at virtual address 0 (identity mapping)
- * and PAGE_OFFSET for up to _end.
- *
- * FIXME: This code is taken verbatim from arch/x86/kernel/head_32.S: they
- * don't have a stack at this point, so we can't just use call and ret.
- */
-init_pagetables:
-#if PTRS_PER_PMD > 1
-#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD)
-#else
-#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
-#endif
-#define pa(X) ((X) - __PAGE_OFFSET)
-
-/* Enough space to fit pagetables for the low memory linear map */
-MAPPING_BEYOND_END = \
-	PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT
-#ifdef CONFIG_X86_PAE
-
-	/*
-	 * In PAE mode initial_page_table is statically defined to contain
-	 * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3
-	 * entries). The identity mapping is handled by pointing two PGD entries
-	 * to the first kernel PMD.
-	 *
-	 * Note the upper half of each PMD or PTE are always zero at this stage.
-	 */
-
-#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
-
-	xorl %ebx,%ebx				/* %ebx is kept at zero */
-
-	movl $pa(__brk_base), %edi
-	movl $pa(initial_pg_pmd), %edx
-	movl $PTE_IDENT_ATTR, %eax
-10:
-	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PMD entry */
-	movl %ecx,(%edx)			/* Store PMD entry */
-						/* Upper half already zero */
-	addl $8,%edx
-	movl $512,%ecx
-11:
-	stosl
-	xchgl %eax,%ebx
-	stosl
-	xchgl %eax,%ebx
-	addl $0x1000,%eax
-	loop 11b
-
-	/*
-	 * End condition: we must map up to the end + MAPPING_BEYOND_END.
-	 */
-	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
-	cmpl %ebp,%eax
-	jb 10b
-1:
-	addl $__PAGE_OFFSET, %edi
-	movl %edi, pa(_brk_end)
-	shrl $12, %eax
-	movl %eax, pa(max_pfn_mapped)
-
-	/* Do early initialization of the fixmap area */
-	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
-	movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8)
-#else	/* Not PAE */
-
-page_pde_offset = (__PAGE_OFFSET >> 20);
-
-	movl $pa(__brk_base), %edi
-	movl $pa(initial_page_table), %edx
-	movl $PTE_IDENT_ATTR, %eax
-10:
-	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PDE entry */
-	movl %ecx,(%edx)			/* Store identity PDE entry */
-	movl %ecx,page_pde_offset(%edx)		/* Store kernel PDE entry */
-	addl $4,%edx
-	movl $1024, %ecx
-11:
-	stosl
-	addl $0x1000,%eax
-	loop 11b
-	/*
-	 * End condition: we must map up to the end + MAPPING_BEYOND_END.
-	 */
-	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
-	cmpl %ebp,%eax
-	jb 10b
-	addl $__PAGE_OFFSET, %edi
-	movl %edi, pa(_brk_end)
-	shrl $12, %eax
-	movl %eax, pa(max_pfn_mapped)
-
-	/* Do early initialization of the fixmap area */
-	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
-	movl %eax,pa(initial_page_table+0xffc)
-#endif
-	ret
-
 /*G:055
  * We create a macro which puts the assembler code between lgstart_ and lgend_
  * markers.  These templates are put in the .text section: they can't be

arch/x86/mm/Makefile

@@ -23,7 +23,7 @@ mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
 obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
-obj-$(CONFIG_K8_NUMA)		+= k8topology_64.o
+obj-$(CONFIG_AMD_NUMA)		+= amdtopology_64.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat_$(BITS).o
 
 obj-$(CONFIG_HAVE_MEMBLOCK)		+= memblock.o

arch/x86/mm/k8topology_64.c → arch/x86/mm/amdtopology_64.c

@@ -1,8 +1,8 @@
 /*
- * AMD K8 NUMA support.
+ * AMD NUMA support.
  * Discover the memory map and associated nodes.
  *
- * This version reads it directly from the K8 northbridge.
+ * This version reads it directly from the AMD northbridge.
  *
  * Copyright 2002,2003 Andi Kleen, SuSE Labs.
  */
@@ -57,7 +57,7 @@ static __init void early_get_boot_cpu_id(void)
 {
 	/*
 	 * need to get the APIC ID of the BSP so can use that to
-	 * create apicid_to_node in k8_scan_nodes()
+	 * create apicid_to_node in amd_scan_nodes()
 	 */
 #ifdef CONFIG_X86_MPPARSE
 	/*
@@ -69,7 +69,7 @@ static __init void early_get_boot_cpu_id(void)
 	early_init_lapic_mapping();
 }
 
-int __init k8_get_nodes(struct bootnode *physnodes)
+int __init amd_get_nodes(struct bootnode *physnodes)
 {
 	int i;
 	int ret = 0;
@@ -82,7 +82,7 @@ int __init k8_get_nodes(struct bootnode *physnodes)
 	return ret;
 }
 
-int __init k8_numa_init(unsigned long start_pfn, unsigned long end_pfn)
+int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long start = PFN_PHYS(start_pfn);
 	unsigned long end = PFN_PHYS(end_pfn);
@@ -194,7 +194,7 @@ int __init k8_numa_init(unsigned long start_pfn, unsigned long end_pfn)
 	return 0;
 }
 
-int __init k8_scan_nodes(void)
+int __init amd_scan_nodes(void)
 {
 	unsigned int bits;
 	unsigned int cores;

arch/x86/mm/init.c

@@ -364,8 +364,9 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	/*
 	 * We just marked the kernel text read only above, now that
 	 * we are going to free part of that, we need to make that
-	 * writeable first.
+	 * writeable and non-executable first.
 	 */
+	set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
 	set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
 
 	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);

arch/x86/mm/init_32.c

@@ -226,7 +226,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
 
 static inline int is_kernel_text(unsigned long addr)
 {
-	if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end)
+	if (addr >= (unsigned long)_text && addr <= (unsigned long)__init_end)
 		return 1;
 	return 0;
 }
@@ -912,6 +912,23 @@ void set_kernel_text_ro(void)
 	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 }
 
+static void mark_nxdata_nx(void)
+{
+	/*
+	 * When this called, init has already been executed and released,
+	 * so everything past _etext sould be NX.
+	 */
+	unsigned long start = PFN_ALIGN(_etext);
+	/*
+	 * This comes from is_kernel_text upper limit. Also HPAGE where used:
+	 */
+	unsigned long size = (((unsigned long)__init_end + HPAGE_SIZE) & HPAGE_MASK) - start;
+
+	if (__supported_pte_mask & _PAGE_NX)
+		printk(KERN_INFO "NX-protecting the kernel data: %luk\n", size >> 10);
+	set_pages_nx(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
@@ -946,6 +963,7 @@ void mark_rodata_ro(void)
 	printk(KERN_INFO "Testing CPA: write protecting again\n");
 	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 #endif
+	mark_nxdata_nx();
 }
 #endif
 

arch/x86/mm/numa_64.c

@@ -264,7 +264,7 @@ static struct bootnode physnodes[MAX_NUMNODES] __initdata;
 static char *cmdline __initdata;
 
 static int __init setup_physnodes(unsigned long start, unsigned long end,
-					int acpi, int k8)
+					int acpi, int amd)
 {
 	int nr_nodes = 0;
 	int ret = 0;
@@ -274,13 +274,13 @@ static int __init setup_physnodes(unsigned long start, unsigned long end,
 	if (acpi)
 		nr_nodes = acpi_get_nodes(physnodes);
 #endif
-#ifdef CONFIG_K8_NUMA
-	if (k8)
-		nr_nodes = k8_get_nodes(physnodes);
+#ifdef CONFIG_AMD_NUMA
+	if (amd)
+		nr_nodes = amd_get_nodes(physnodes);
 #endif
 	/*
 	 * Basic sanity checking on the physical node map: there may be errors
-	 * if the SRAT or K8 incorrectly reported the topology or the mem=
+	 * if the SRAT or AMD code incorrectly reported the topology or the mem=
 	 * kernel parameter is used.
 	 */
 	for (i = 0; i < nr_nodes; i++) {
@@ -549,7 +549,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
  * numa=fake command-line option.
  */
 static int __init numa_emulation(unsigned long start_pfn,
-			unsigned long last_pfn, int acpi, int k8)
+			unsigned long last_pfn, int acpi, int amd)
 {
 	u64 addr = start_pfn << PAGE_SHIFT;
 	u64 max_addr = last_pfn << PAGE_SHIFT;
@@ -557,7 +557,7 @@ static int __init numa_emulation(unsigned long start_pfn,
 	int num_nodes;
 	int i;
 
-	num_phys_nodes = setup_physnodes(addr, max_addr, acpi, k8);
+	num_phys_nodes = setup_physnodes(addr, max_addr, acpi, amd);
 	/*
 	 * If the numa=fake command-line contains a 'M' or 'G', it represents
 	 * the fixed node size.  Otherwise, if it is just a single number N,
@@ -602,7 +602,7 @@ static int __init numa_emulation(unsigned long start_pfn,
 #endif /* CONFIG_NUMA_EMU */
 
 void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
-				int acpi, int k8)
+				int acpi, int amd)
 {
 	int i;
 
@@ -610,7 +610,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
 	nodes_clear(node_online_map);
 
 #ifdef CONFIG_NUMA_EMU
-	if (cmdline && !numa_emulation(start_pfn, last_pfn, acpi, k8))
+	if (cmdline && !numa_emulation(start_pfn, last_pfn, acpi, amd))
 		return;
 	nodes_clear(node_possible_map);
 	nodes_clear(node_online_map);
@@ -624,8 +624,8 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn,
 	nodes_clear(node_online_map);
 #endif
 
-#ifdef CONFIG_K8_NUMA
-	if (!numa_off && k8 && !k8_scan_nodes())
+#ifdef CONFIG_AMD_NUMA
+	if (!numa_off && amd && !amd_scan_nodes())
 		return;
 	nodes_clear(node_possible_map);
 	nodes_clear(node_online_map);

arch/x86/mm/pageattr.c

@@ -13,6 +13,7 @@
 #include <linux/pfn.h>
 #include <linux/percpu.h>
 #include <linux/gfp.h>
+#include <linux/pci.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
@@ -255,13 +256,16 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 				   unsigned long pfn)
 {
 	pgprot_t forbidden = __pgprot(0);
+	pgprot_t required = __pgprot(0);
 
 	/*
 	 * The BIOS area between 640k and 1Mb needs to be executable for
 	 * PCI BIOS based config access (CONFIG_PCI_GOBIOS) support.
 	 */
-	if (within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT))
+#ifdef CONFIG_PCI_BIOS
+	if (pcibios_enabled && within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT))
 		pgprot_val(forbidden) |= _PAGE_NX;
+#endif
 
 	/*
 	 * The kernel text needs to be executable for obvious reasons
@@ -278,6 +282,12 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 	if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT,
 		   __pa((unsigned long)__end_rodata) >> PAGE_SHIFT))
 		pgprot_val(forbidden) |= _PAGE_RW;
+	/*
+	 * .data and .bss should always be writable.
+	 */
+	if (within(address, (unsigned long)_sdata, (unsigned long)_edata) ||
+	    within(address, (unsigned long)__bss_start, (unsigned long)__bss_stop))
+		pgprot_val(required) |= _PAGE_RW;
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
 	/*
@@ -317,6 +327,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 #endif
 
 	prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));
+	prot = __pgprot(pgprot_val(prot) | pgprot_val(required));
 
 	return prot;
 }
@@ -393,7 +404,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 {
 	unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn;
 	pte_t new_pte, old_pte, *tmp;
-	pgprot_t old_prot, new_prot;
+	pgprot_t old_prot, new_prot, req_prot;
 	int i, do_split = 1;
 	unsigned int level;
 
@@ -438,10 +449,10 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * We are safe now. Check whether the new pgprot is the same:
 	 */
 	old_pte = *kpte;
-	old_prot = new_prot = pte_pgprot(old_pte);
+	old_prot = new_prot = req_prot = pte_pgprot(old_pte);
 
-	pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr);
-	pgprot_val(new_prot) |= pgprot_val(cpa->mask_set);
+	pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr);
+	pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
 
 	/*
 	 * old_pte points to the large page base address. So we need
@@ -450,17 +461,17 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT);
 	cpa->pfn = pfn;
 
-	new_prot = static_protections(new_prot, address, pfn);
+	new_prot = static_protections(req_prot, address, pfn);
 
 	/*
 	 * We need to check the full range, whether
 	 * static_protection() requires a different pgprot for one of
 	 * the pages in the range we try to preserve:
 	 */
-	addr = address + PAGE_SIZE;
-	pfn++;
-	for (i = 1; i < cpa->numpages; i++, addr += PAGE_SIZE, pfn++) {
-		pgprot_t chk_prot = static_protections(new_prot, addr, pfn);
+	addr = address & pmask;
+	pfn = pte_pfn(old_pte);
+	for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) {
+		pgprot_t chk_prot = static_protections(req_prot, addr, pfn);
 
 		if (pgprot_val(chk_prot) != pgprot_val(new_prot))
 			goto out_unlock;
@@ -483,7 +494,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * that we limited the number of possible pages already to
 	 * the number of pages in the large page.
 	 */
-	if (address == (nextpage_addr - psize) && cpa->numpages == numpages) {
+	if (address == (address & pmask) && cpa->numpages == (psize >> PAGE_SHIFT)) {
 		/*
 		 * The address is aligned and the number of pages
 		 * covers the full page.

arch/x86/mm/setup_nx.c

@@ -41,7 +41,7 @@ void __init x86_report_nx(void)
 {
 	if (!cpu_has_nx) {
 		printk(KERN_NOTICE "Notice: NX (Execute Disable) protection "
-		       "missing in CPU or disabled in BIOS!\n");
+		       "missing in CPU!\n");
 	} else {
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 		if (disable_nx) {

arch/x86/mm/srat_32.c

@@ -92,6 +92,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *cpu_affinity)
 	/* mark this node as "seen" in node bitmap */
 	BMAP_SET(pxm_bitmap, cpu_affinity->proximity_domain_lo);
 
+	/* don't need to check apic_id here, because it is always 8 bits */
 	apicid_to_pxm[cpu_affinity->apic_id] = cpu_affinity->proximity_domain_lo;
 
 	printk(KERN_DEBUG "CPU %02x in proximity domain %02x\n",

arch/x86/mm/srat_64.c

@@ -134,6 +134,10 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 	}
 
 	apic_id = pa->apic_id;
+	if (apic_id >= MAX_LOCAL_APIC) {
+		printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
+		return;
+	}
 	apicid_to_node[apic_id] = node;
 	node_set(node, cpu_nodes_parsed);
 	acpi_numa = 1;
@@ -168,6 +172,12 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 		apic_id = (pa->apic_id << 8) | pa->local_sapic_eid;
 	else
 		apic_id = pa->apic_id;
+
+	if (apic_id >= MAX_LOCAL_APIC) {
+		printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
+		return;
+	}
+
 	apicid_to_node[apic_id] = node;
 	node_set(node, cpu_nodes_parsed);
 	acpi_numa = 1;

arch/x86/oprofile/op_model_amd.c

@@ -610,6 +610,7 @@ static int force_ibs_eilvt_setup(void)
 		ret = setup_ibs_ctl(i);
 		if (ret)
 			return ret;
+		pr_err(FW_BUG "using offset %d for IBS interrupts\n", i);
 		return 0;
 	}
 

arch/x86/pci/Makefile

@@ -7,6 +7,7 @@ obj-$(CONFIG_PCI_OLPC)		+= olpc.o
 obj-$(CONFIG_PCI_XEN)		+= xen.o
 
 obj-y				+= fixup.o
+obj-$(CONFIG_X86_INTEL_CE)      += ce4100.o
 obj-$(CONFIG_ACPI)		+= acpi.o
 obj-y				+= legacy.o irq.o
 

arch/x86/pci/ce4100.c

@@ -0,0 +1,315 @@
+/*
+ *  GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2010 Intel Corporation. All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  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.  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.
+ *  The full GNU General Public License is included in this distribution
+ *  in the file called LICENSE.GPL.
+ *
+ *  Contact Information:
+ *    Intel Corporation
+ *    2200 Mission College Blvd.
+ *    Santa Clara, CA  97052
+ *
+ * This provides access methods for PCI registers that mis-behave on
+ * the CE4100. Each register can be assigned a private init, read and
+ * write routine. The exception to this is the bridge device.  The
+ * bridge device is the only device on bus zero (0) that requires any
+ * fixup so it is a special case ATM
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+
+#include <asm/pci_x86.h>
+
+struct sim_reg {
+	u32 value;
+	u32 mask;
+};
+
+struct sim_dev_reg {
+	int dev_func;
+	int reg;
+	void (*init)(struct sim_dev_reg *reg);
+	void (*read)(struct sim_dev_reg *reg, u32 *value);
+	void (*write)(struct sim_dev_reg *reg, u32 value);
+	struct sim_reg sim_reg;
+};
+
+struct sim_reg_op {
+	void (*init)(struct sim_dev_reg *reg);
+	void (*read)(struct sim_dev_reg *reg, u32 value);
+	void (*write)(struct sim_dev_reg *reg, u32 value);
+};
+
+#define MB (1024 * 1024)
+#define KB (1024)
+#define SIZE_TO_MASK(size) (~(size - 1))
+
+#define DEFINE_REG(device, func, offset, size, init_op, read_op, write_op)\
+{ PCI_DEVFN(device, func), offset, init_op, read_op, write_op,\
+	{0, SIZE_TO_MASK(size)} },
+
+static void reg_init(struct sim_dev_reg *reg)
+{
+	pci_direct_conf1.read(0, 1, reg->dev_func, reg->reg, 4,
+			      &reg->sim_reg.value);
+}
+
+static void reg_read(struct sim_dev_reg *reg, u32 *value)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&pci_config_lock, flags);
+	*value = reg->sim_reg.value;
+	raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+}
+
+static void reg_write(struct sim_dev_reg *reg, u32 value)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&pci_config_lock, flags);
+	reg->sim_reg.value = (value & reg->sim_reg.mask) |
+		(reg->sim_reg.value & ~reg->sim_reg.mask);
+	raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+}
+
+static void sata_reg_init(struct sim_dev_reg *reg)
+{
+	pci_direct_conf1.read(0, 1, PCI_DEVFN(14, 0), 0x10, 4,
+			      &reg->sim_reg.value);
+	reg->sim_reg.value += 0x400;
+}
+
+static void ehci_reg_read(struct sim_dev_reg *reg, u32 *value)
+{
+	reg_read(reg, value);
+	if (*value != reg->sim_reg.mask)
+		*value |= 0x100;
+}
+
+void sata_revid_init(struct sim_dev_reg *reg)
+{
+	reg->sim_reg.value = 0x01060100;
+	reg->sim_reg.mask = 0;
+}
+
+static void sata_revid_read(struct sim_dev_reg *reg, u32 *value)
+{
+	reg_read(reg, value);
+}
+
+static struct sim_dev_reg bus1_fixups[] = {
+	DEFINE_REG(2, 0, 0x10, (16*MB), reg_init, reg_read, reg_write)
+	DEFINE_REG(2, 0, 0x14, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(2, 1, 0x10, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(3, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(4, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(4, 1, 0x10, (128*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(6, 0, 0x10, (512*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(6, 1, 0x10, (512*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(6, 2, 0x10, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(8, 0, 0x10, (1*MB), reg_init, reg_read, reg_write)
+	DEFINE_REG(8, 1, 0x10, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(8, 2, 0x10, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(9, 0, 0x10 , (1*MB), reg_init, reg_read, reg_write)
+	DEFINE_REG(9, 0, 0x14, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(10, 0, 0x10, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(10, 0, 0x14, (256*MB), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 0, 0x10, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 0, 0x14, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 1, 0x10, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 2, 0x10, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 2, 0x14, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 2, 0x18, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 3, 0x10, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 3, 0x14, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 4, 0x10, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 5, 0x10, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 6, 0x10, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 7, 0x10, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(12, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(12, 0, 0x14, (256), reg_init, reg_read, reg_write)
+	DEFINE_REG(12, 1, 0x10, (1024), reg_init, reg_read, reg_write)
+	DEFINE_REG(13, 0, 0x10, (32*KB), reg_init, ehci_reg_read, reg_write)
+	DEFINE_REG(13, 1, 0x10, (32*KB), reg_init, ehci_reg_read, reg_write)
+	DEFINE_REG(14, 0, 0x8,  0, sata_revid_init, sata_revid_read, 0)
+	DEFINE_REG(14, 0, 0x10, 0, reg_init, reg_read, reg_write)
+	DEFINE_REG(14, 0, 0x14, 0, reg_init, reg_read, reg_write)
+	DEFINE_REG(14, 0, 0x18, 0, reg_init, reg_read, reg_write)
+	DEFINE_REG(14, 0, 0x1C, 0, reg_init, reg_read, reg_write)
+	DEFINE_REG(14, 0, 0x20, 0, reg_init, reg_read, reg_write)
+	DEFINE_REG(14, 0, 0x24, (0x200), sata_reg_init, reg_read, reg_write)
+	DEFINE_REG(15, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(15, 0, 0x14, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(16, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(16, 0, 0x14, (64*MB), reg_init, reg_read, reg_write)
+	DEFINE_REG(16, 0, 0x18, (64*MB), reg_init, reg_read, reg_write)
+	DEFINE_REG(17, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(18, 0, 0x10, (1*KB), reg_init, reg_read, reg_write)
+};
+
+static void __init init_sim_regs(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) {
+		if (bus1_fixups[i].init)
+			bus1_fixups[i].init(&bus1_fixups[i]);
+	}
+}
+
+static inline void extract_bytes(u32 *value, int reg, int len)
+{
+	uint32_t mask;
+
+	*value >>= ((reg & 3) * 8);
+	mask = 0xFFFFFFFF >> ((4 - len) * 8);
+	*value &= mask;
+}
+
+int bridge_read(unsigned int devfn, int reg, int len, u32 *value)
+{
+	u32 av_bridge_base, av_bridge_limit;
+	int retval = 0;
+
+	switch (reg) {
+	/* Make BARs appear to not request any memory. */
+	case PCI_BASE_ADDRESS_0:
+	case PCI_BASE_ADDRESS_0 + 1:
+	case PCI_BASE_ADDRESS_0 + 2:
+	case PCI_BASE_ADDRESS_0 + 3:
+		*value = 0;
+		break;
+
+		/* Since subordinate bus number register is hardwired
+		 * to zero and read only, so do the simulation.
+		 */
+	case PCI_PRIMARY_BUS:
+		if (len == 4)
+			*value = 0x00010100;
+		break;
+
+	case PCI_SUBORDINATE_BUS:
+		*value = 1;
+		break;
+
+	case PCI_MEMORY_BASE:
+	case PCI_MEMORY_LIMIT:
+		/* Get the A/V bridge base address. */
+		pci_direct_conf1.read(0, 0, devfn,
+				PCI_BASE_ADDRESS_0, 4, &av_bridge_base);
+
+		av_bridge_limit = av_bridge_base + (512*MB - 1);
+		av_bridge_limit >>= 16;
+		av_bridge_limit &= 0xFFF0;
+
+		av_bridge_base >>= 16;
+		av_bridge_base &= 0xFFF0;
+
+		if (reg == PCI_MEMORY_LIMIT)
+			*value = av_bridge_limit;
+		else if (len == 2)
+			*value = av_bridge_base;
+		else
+			*value = (av_bridge_limit << 16) | av_bridge_base;
+		break;
+		/* Make prefetchable memory limit smaller than prefetchable
+		 * memory base, so not claim prefetchable memory space.
+		 */
+	case PCI_PREF_MEMORY_BASE:
+		*value = 0xFFF0;
+		break;
+	case PCI_PREF_MEMORY_LIMIT:
+		*value = 0x0;
+		break;
+		/* Make IO limit smaller than IO base, so not claim IO space. */
+	case PCI_IO_BASE:
+		*value = 0xF0;
+		break;
+	case PCI_IO_LIMIT:
+		*value = 0;
+		break;
+	default:
+		retval = 1;
+	}
+	return retval;
+}
+
+static int ce4100_conf_read(unsigned int seg, unsigned int bus,
+			    unsigned int devfn, int reg, int len, u32 *value)
+{
+	int i, retval = 1;
+
+	if (bus == 1) {
+		for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) {
+			if (bus1_fixups[i].dev_func == devfn &&
+			    bus1_fixups[i].reg == (reg & ~3) &&
+			    bus1_fixups[i].read) {
+				bus1_fixups[i].read(&(bus1_fixups[i]),
+						    value);
+				extract_bytes(value, reg, len);
+				return 0;
+			}
+		}
+	}
+
+	if (bus == 0 && (PCI_DEVFN(1, 0) == devfn) &&
+	    !bridge_read(devfn, reg, len, value))
+		return 0;
+
+	return pci_direct_conf1.read(seg, bus, devfn, reg, len, value);
+}
+
+static int ce4100_conf_write(unsigned int seg, unsigned int bus,
+			     unsigned int devfn, int reg, int len, u32 value)
+{
+	int i;
+
+	if (bus == 1) {
+		for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) {
+			if (bus1_fixups[i].dev_func == devfn &&
+			    bus1_fixups[i].reg == (reg & ~3) &&
+			    bus1_fixups[i].write) {
+				bus1_fixups[i].write(&(bus1_fixups[i]),
+						     value);
+				return 0;
+			}
+		}
+	}
+
+	/* Discard writes to A/V bridge BAR. */
+	if (bus == 0 && PCI_DEVFN(1, 0) == devfn &&
+	    ((reg & ~3) == PCI_BASE_ADDRESS_0))
+		return 0;
+
+	return pci_direct_conf1.write(seg, bus, devfn, reg, len, value);
+}
+
+struct pci_raw_ops ce4100_pci_conf = {
+	.read =	ce4100_conf_read,
+	.write = ce4100_conf_write,
+};
+
+static int __init ce4100_pci_init(void)
+{
+	init_sim_regs();
+	raw_pci_ops = &ce4100_pci_conf;
+	return 0;
+}
+subsys_initcall(ce4100_pci_init);

arch/x86/pci/pcbios.c

@@ -9,6 +9,7 @@
 #include <linux/uaccess.h>
 #include <asm/pci_x86.h>
 #include <asm/pci-functions.h>
+#include <asm/cacheflush.h>
 
 /* BIOS32 signature: "_32_" */
 #define BIOS32_SIGNATURE	(('_' << 0) + ('3' << 8) + ('2' << 16) + ('_' << 24))
@@ -25,6 +26,27 @@
 #define PCIBIOS_HW_TYPE1_SPEC		0x10
 #define PCIBIOS_HW_TYPE2_SPEC		0x20
 
+int pcibios_enabled;
+
+/* According to the BIOS specification at:
+ * http://members.datafast.net.au/dft0802/specs/bios21.pdf, we could
+ * restrict the x zone to some pages and make it ro. But this may be
+ * broken on some bios, complex to handle with static_protections.
+ * We could make the 0xe0000-0x100000 range rox, but this can break
+ * some ISA mapping.
+ *
+ * So we let's an rw and x hole when pcibios is used. This shouldn't
+ * happen for modern system with mmconfig, and if you don't want it
+ * you could disable pcibios...
+ */
+static inline void set_bios_x(void)
+{
+	pcibios_enabled = 1;
+	set_memory_x(PAGE_OFFSET + BIOS_BEGIN, (BIOS_END - BIOS_BEGIN) >> PAGE_SHIFT);
+	if (__supported_pte_mask & _PAGE_NX)
+		printk(KERN_INFO "PCI : PCI BIOS aera is rw and x. Use pci=nobios if you want it NX.\n");
+}
+
 /*
  * This is the standard structure used to identify the entry point
  * to the BIOS32 Service Directory, as documented in
@@ -332,6 +354,7 @@ static struct pci_raw_ops * __devinit pci_find_bios(void)
 			DBG("PCI: BIOS32 Service Directory entry at 0x%lx\n",
 					bios32_entry);
 			bios32_indirect.address = bios32_entry + PAGE_OFFSET;
+			set_bios_x();
 			if (check_pcibios())
 				return &pci_bios_access;
 		}

arch/x86/platform/Makefile

@@ -1,5 +1,7 @@
 # Platform specific code goes here
+obj-y	+= ce4100/
 obj-y	+= efi/
+obj-y	+= iris/
 obj-y	+= mrst/
 obj-y	+= olpc/
 obj-y	+= scx200/

arch/x86/platform/ce4100/Makefile

@@ -0,0 +1 @@
+obj-$(CONFIG_X86_INTEL_CE)	+= ce4100.o

arch/x86/platform/ce4100/ce4100.c

@@ -0,0 +1,132 @@
+/*
+ * Intel CE4100  platform specific setup code
+ *
+ * (C) Copyright 2010 Intel Corporation
+ *
+ * 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; version 2
+ * of the License.
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/serial_reg.h>
+#include <linux/serial_8250.h>
+
+#include <asm/setup.h>
+#include <asm/io.h>
+
+static int ce4100_i8042_detect(void)
+{
+	return 0;
+}
+
+static void __init sdv_find_smp_config(void)
+{
+}
+
+#ifdef CONFIG_SERIAL_8250
+
+
+static unsigned int mem_serial_in(struct uart_port *p, int offset)
+{
+	offset = offset << p->regshift;
+	return readl(p->membase + offset);
+}
+
+/*
+ * The UART Tx interrupts are not set under some conditions and therefore serial
+ * transmission hangs. This is a silicon issue and has not been root caused. The
+ * workaround for this silicon issue checks UART_LSR_THRE bit and UART_LSR_TEMT
+ * bit of LSR register in interrupt handler to see whether at least one of these
+ * two bits is set, if so then process the transmit request. If this workaround
+ * is not applied, then the serial transmission may hang. This workaround is for
+ * errata number 9 in Errata - B step.
+*/
+
+static unsigned int ce4100_mem_serial_in(struct uart_port *p, int offset)
+{
+	unsigned int ret, ier, lsr;
+
+	if (offset == UART_IIR) {
+		offset = offset << p->regshift;
+		ret = readl(p->membase + offset);
+		if (ret & UART_IIR_NO_INT) {
+			/* see if the TX interrupt should have really set */
+			ier = mem_serial_in(p, UART_IER);
+			/* see if the UART's XMIT interrupt is enabled */
+			if (ier & UART_IER_THRI) {
+				lsr = mem_serial_in(p, UART_LSR);
+				/* now check to see if the UART should be
+				   generating an interrupt (but isn't) */
+				if (lsr & (UART_LSR_THRE | UART_LSR_TEMT))
+					ret &= ~UART_IIR_NO_INT;
+			}
+		}
+	} else
+		ret =  mem_serial_in(p, offset);
+	return ret;
+}
+
+static void ce4100_mem_serial_out(struct uart_port *p, int offset, int value)
+{
+	offset = offset << p->regshift;
+	writel(value, p->membase + offset);
+}
+
+static void ce4100_serial_fixup(int port, struct uart_port *up,
+	unsigned short *capabilites)
+{
+#ifdef CONFIG_EARLY_PRINTK
+	/*
+	 * Over ride the legacy port configuration that comes from
+	 * asm/serial.h. Using the ioport driver then switching to the
+	 * PCI memmaped driver hangs the IOAPIC
+	 */
+	if (up->iotype !=  UPIO_MEM32) {
+		up->uartclk  = 14745600;
+		up->mapbase = 0xdffe0200;
+		set_fixmap_nocache(FIX_EARLYCON_MEM_BASE,
+				up->mapbase & PAGE_MASK);
+		up->membase =
+			(void __iomem *)__fix_to_virt(FIX_EARLYCON_MEM_BASE);
+		up->membase += up->mapbase & ~PAGE_MASK;
+		up->iotype   = UPIO_MEM32;
+		up->regshift = 2;
+	}
+#endif
+	up->iobase = 0;
+	up->serial_in = ce4100_mem_serial_in;
+	up->serial_out = ce4100_mem_serial_out;
+
+	*capabilites |= (1 << 12);
+}
+
+static __init void sdv_serial_fixup(void)
+{
+	serial8250_set_isa_configurator(ce4100_serial_fixup);
+}
+
+#else
+static inline void sdv_serial_fixup(void);
+#endif
+
+static void __init sdv_arch_setup(void)
+{
+	sdv_serial_fixup();
+}
+
+/*
+ * CE4100 specific x86_init function overrides and early setup
+ * calls.
+ */
+void __init x86_ce4100_early_setup(void)
+{
+	x86_init.oem.arch_setup = sdv_arch_setup;
+	x86_platform.i8042_detect = ce4100_i8042_detect;
+	x86_init.resources.probe_roms = x86_init_noop;
+	x86_init.mpparse.get_smp_config = x86_init_uint_noop;
+	x86_init.mpparse.find_smp_config = sdv_find_smp_config;
+}

arch/x86/platform/iris/Makefile

@@ -0,0 +1 @@
+obj-$(CONFIG_X86_32_IRIS)		+= iris.o

arch/x86/platform/iris/iris.c

@@ -0,0 +1,91 @@
+/*
+ * Eurobraille/Iris power off support.
+ *
+ * Eurobraille's Iris machine is a PC with no APM or ACPI support.
+ * It is shutdown by a special I/O sequence which this module provides.
+ *
+ *  Copyright (C) Shérab <Sebastien.Hinderer@ens-lyon.org>
+ *
+ * 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. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with the program ; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/moduleparam.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/pm.h>
+#include <asm/io.h>
+
+#define IRIS_GIO_BASE		0x340
+#define IRIS_GIO_INPUT		IRIS_GIO_BASE
+#define IRIS_GIO_OUTPUT		(IRIS_GIO_BASE + 1)
+#define IRIS_GIO_PULSE		0x80 /* First byte to send */
+#define IRIS_GIO_REST		0x00 /* Second byte to send */
+#define IRIS_GIO_NODEV		0xff /* Likely not an Iris */
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Sébastien Hinderer <Sebastien.Hinderer@ens-lyon.org>");
+MODULE_DESCRIPTION("A power_off handler for Iris devices from EuroBraille");
+MODULE_SUPPORTED_DEVICE("Eurobraille/Iris");
+
+static int force;
+
+module_param(force, bool, 0);
+MODULE_PARM_DESC(force, "Set to one to force poweroff handler installation.");
+
+static void (*old_pm_power_off)(void);
+
+static void iris_power_off(void)
+{
+	outb(IRIS_GIO_PULSE, IRIS_GIO_OUTPUT);
+	msleep(850);
+	outb(IRIS_GIO_REST, IRIS_GIO_OUTPUT);
+}
+
+/*
+ * Before installing the power_off handler, try to make sure the OS is
+ * running on an Iris.  Since Iris does not support DMI, this is done
+ * by reading its input port and seeing whether the read value is
+ * meaningful.
+ */
+static int iris_init(void)
+{
+	unsigned char status;
+	if (force != 1) {
+		printk(KERN_ERR "The force parameter has not been set to 1 so the Iris poweroff handler will not be installed.\n");
+		return -ENODEV;
+	}
+	status = inb(IRIS_GIO_INPUT);
+	if (status == IRIS_GIO_NODEV) {
+		printk(KERN_ERR "This machine does not seem to be an Iris. Power_off handler not installed.\n");
+		return -ENODEV;
+	}
+	old_pm_power_off = pm_power_off;
+	pm_power_off = &iris_power_off;
+	printk(KERN_INFO "Iris power_off handler installed.\n");
+
+	return 0;
+}
+
+static void iris_exit(void)
+{
+	pm_power_off = old_pm_power_off;
+	printk(KERN_INFO "Iris power_off handler uninstalled.\n");
+}
+
+module_init(iris_init);
+module_exit(iris_exit);

arch/x86/platform/mrst/Makefile

@@ -1 +1,3 @@
 obj-$(CONFIG_X86_MRST)		+= mrst.o
+obj-$(CONFIG_X86_MRST)		+= vrtc.o
+obj-$(CONFIG_EARLY_PRINTK_MRST)	+= early_printk_mrst.o

arch/x86/platform/mrst/mrst.c

@@ -9,9 +9,19 @@
  * as published by the Free Software Foundation; version 2
  * of the License.
  */
+
+#define pr_fmt(fmt) "mrst: " fmt
+
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/sfi.h>
+#include <linux/intel_pmic_gpio.h>
+#include <linux/spi/spi.h>
+#include <linux/i2c.h>
+#include <linux/i2c/pca953x.h>
+#include <linux/gpio_keys.h>
+#include <linux/input.h>
+#include <linux/platform_device.h>
 #include <linux/irq.h>
 #include <linux/module.h>
 
@@ -23,7 +33,9 @@
 #include <asm/mrst.h>
 #include <asm/io.h>
 #include <asm/i8259.h>
+#include <asm/intel_scu_ipc.h>
 #include <asm/apb_timer.h>
+#include <asm/reboot.h>
 
 /*
  * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock,
@@ -102,10 +114,10 @@ static int __init sfi_parse_mtmr(struct sfi_table_header *table)
 		memcpy(sfi_mtimer_array, pentry, totallen);
 	}
 
-	printk(KERN_INFO "SFI: MTIMER info (num = %d):\n", sfi_mtimer_num);
+	pr_debug("SFI MTIMER info (num = %d):\n", sfi_mtimer_num);
 	pentry = sfi_mtimer_array;
 	for (totallen = 0; totallen < sfi_mtimer_num; totallen++, pentry++) {
-		printk(KERN_INFO "timer[%d]: paddr = 0x%08x, freq = %dHz,"
+		pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz,"
 			" irq = %d\n", totallen, (u32)pentry->phys_addr,
 			pentry->freq_hz, pentry->irq);
 			if (!pentry->irq)
@@ -176,14 +188,14 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
 		memcpy(sfi_mrtc_array, pentry, totallen);
 	}
 
-	printk(KERN_INFO "SFI: RTC info (num = %d):\n", sfi_mrtc_num);
+	pr_debug("SFI RTC info (num = %d):\n", sfi_mrtc_num);
 	pentry = sfi_mrtc_array;
 	for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) {
-		printk(KERN_INFO "RTC[%d]: paddr = 0x%08x, irq = %d\n",
+		pr_debug("RTC[%d]: paddr = 0x%08x, irq = %d\n",
 			totallen, (u32)pentry->phys_addr, pentry->irq);
 		mp_irq.type = MP_IOAPIC;
 		mp_irq.irqtype = mp_INT;
-		mp_irq.irqflag = 0;
+		mp_irq.irqflag = 0xf;	/* level trigger and active low */
 		mp_irq.srcbus = 0;
 		mp_irq.srcbusirq = pentry->irq;	/* IRQ */
 		mp_irq.dstapic = MP_APIC_ALL;
@@ -209,6 +221,7 @@ static unsigned long __init mrst_calibrate_tsc(void)
 
 void __init mrst_time_init(void)
 {
+	sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
 	switch (mrst_timer_options) {
 	case MRST_TIMER_APBT_ONLY:
 		break;
@@ -224,16 +237,10 @@ void __init mrst_time_init(void)
 		return;
 	}
 	/* we need at least one APB timer */
-	sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
 	pre_init_apic_IRQ0();
 	apbt_time_init();
 }
 
-void __init mrst_rtc_init(void)
-{
-	sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc);
-}
-
 void __cpuinit mrst_arch_setup(void)
 {
 	if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27)
@@ -256,6 +263,17 @@ static int mrst_i8042_detect(void)
 	return 0;
 }
 
+/* Reboot and power off are handled by the SCU on a MID device */
+static void mrst_power_off(void)
+{
+	intel_scu_ipc_simple_command(0xf1, 1);
+}
+
+static void mrst_reboot(void)
+{
+	intel_scu_ipc_simple_command(0xf1, 0);
+}
+
 /*
  * Moorestown specific x86_init function overrides and early setup
  * calls.
@@ -281,6 +299,10 @@ void __init x86_mrst_early_setup(void)
 
 	legacy_pic = &null_legacy_pic;
 
+	/* Moorestown specific power_off/restart method */
+	pm_power_off = mrst_power_off;
+	machine_ops.emergency_restart  = mrst_reboot;
+
 	/* Avoid searching for BIOS MP tables */
 	x86_init.mpparse.find_smp_config = x86_init_noop;
 	x86_init.mpparse.get_smp_config = x86_init_uint_noop;
@@ -309,3 +331,505 @@ static inline int __init setup_x86_mrst_timer(char *arg)
 	return 0;
 }
 __setup("x86_mrst_timer=", setup_x86_mrst_timer);
+
+/*
+ * Parsing GPIO table first, since the DEVS table will need this table
+ * to map the pin name to the actual pin.
+ */
+static struct sfi_gpio_table_entry *gpio_table;
+static int gpio_num_entry;
+
+static int __init sfi_parse_gpio(struct sfi_table_header *table)
+{
+	struct sfi_table_simple *sb;
+	struct sfi_gpio_table_entry *pentry;
+	int num, i;
+
+	if (gpio_table)
+		return 0;
+	sb = (struct sfi_table_simple *)table;
+	num = SFI_GET_NUM_ENTRIES(sb, struct sfi_gpio_table_entry);
+	pentry = (struct sfi_gpio_table_entry *)sb->pentry;
+
+	gpio_table = (struct sfi_gpio_table_entry *)
+				kmalloc(num * sizeof(*pentry), GFP_KERNEL);
+	if (!gpio_table)
+		return -1;
+	memcpy(gpio_table, pentry, num * sizeof(*pentry));
+	gpio_num_entry = num;
+
+	pr_debug("GPIO pin info:\n");
+	for (i = 0; i < num; i++, pentry++)
+		pr_debug("info[%2d]: controller = %16.16s, pin_name = %16.16s,"
+		" pin = %d\n", i,
+			pentry->controller_name,
+			pentry->pin_name,
+			pentry->pin_no);
+	return 0;
+}
+
+static int get_gpio_by_name(const char *name)
+{
+	struct sfi_gpio_table_entry *pentry = gpio_table;
+	int i;
+
+	if (!pentry)
+		return -1;
+	for (i = 0; i < gpio_num_entry; i++, pentry++) {
+		if (!strncmp(name, pentry->pin_name, SFI_NAME_LEN))
+			return pentry->pin_no;
+	}
+	return -1;
+}
+
+/*
+ * Here defines the array of devices platform data that IAFW would export
+ * through SFI "DEVS" table, we use name and type to match the device and
+ * its platform data.
+ */
+struct devs_id {
+	char name[SFI_NAME_LEN + 1];
+	u8 type;
+	u8 delay;
+	void *(*get_platform_data)(void *info);
+};
+
+/* the offset for the mapping of global gpio pin to irq */
+#define MRST_IRQ_OFFSET 0x100
+
+static void __init *pmic_gpio_platform_data(void *info)
+{
+	static struct intel_pmic_gpio_platform_data pmic_gpio_pdata;
+	int gpio_base = get_gpio_by_name("pmic_gpio_base");
+
+	if (gpio_base == -1)
+		gpio_base = 64;
+	pmic_gpio_pdata.gpio_base = gpio_base;
+	pmic_gpio_pdata.irq_base = gpio_base + MRST_IRQ_OFFSET;
+	pmic_gpio_pdata.gpiointr = 0xffffeff8;
+
+	return &pmic_gpio_pdata;
+}
+
+static void __init *max3111_platform_data(void *info)
+{
+	struct spi_board_info *spi_info = info;
+	int intr = get_gpio_by_name("max3111_int");
+
+	if (intr == -1)
+		return NULL;
+	spi_info->irq = intr + MRST_IRQ_OFFSET;
+	return NULL;
+}
+
+/* we have multiple max7315 on the board ... */
+#define MAX7315_NUM 2
+static void __init *max7315_platform_data(void *info)
+{
+	static struct pca953x_platform_data max7315_pdata[MAX7315_NUM];
+	static int nr;
+	struct pca953x_platform_data *max7315 = &max7315_pdata[nr];
+	struct i2c_board_info *i2c_info = info;
+	int gpio_base, intr;
+	char base_pin_name[SFI_NAME_LEN + 1];
+	char intr_pin_name[SFI_NAME_LEN + 1];
+
+	if (nr == MAX7315_NUM) {
+		pr_err("too many max7315s, we only support %d\n",
+				MAX7315_NUM);
+		return NULL;
+	}
+	/* we have several max7315 on the board, we only need load several
+	 * instances of the same pca953x driver to cover them
+	 */
+	strcpy(i2c_info->type, "max7315");
+	if (nr++) {
+		sprintf(base_pin_name, "max7315_%d_base", nr);
+		sprintf(intr_pin_name, "max7315_%d_int", nr);
+	} else {
+		strcpy(base_pin_name, "max7315_base");
+		strcpy(intr_pin_name, "max7315_int");
+	}
+
+	gpio_base = get_gpio_by_name(base_pin_name);
+	intr = get_gpio_by_name(intr_pin_name);
+
+	if (gpio_base == -1)
+		return NULL;
+	max7315->gpio_base = gpio_base;
+	if (intr != -1) {
+		i2c_info->irq = intr + MRST_IRQ_OFFSET;
+		max7315->irq_base = gpio_base + MRST_IRQ_OFFSET;
+	} else {
+		i2c_info->irq = -1;
+		max7315->irq_base = -1;
+	}
+	return max7315;
+}
+
+static void __init *emc1403_platform_data(void *info)
+{
+	static short intr2nd_pdata;
+	struct i2c_board_info *i2c_info = info;
+	int intr = get_gpio_by_name("thermal_int");
+	int intr2nd = get_gpio_by_name("thermal_alert");
+
+	if (intr == -1 || intr2nd == -1)
+		return NULL;
+
+	i2c_info->irq = intr + MRST_IRQ_OFFSET;
+	intr2nd_pdata = intr2nd + MRST_IRQ_OFFSET;
+
+	return &intr2nd_pdata;
+}
+
+static void __init *lis331dl_platform_data(void *info)
+{
+	static short intr2nd_pdata;
+	struct i2c_board_info *i2c_info = info;
+	int intr = get_gpio_by_name("accel_int");
+	int intr2nd = get_gpio_by_name("accel_2");
+
+	if (intr == -1 || intr2nd == -1)
+		return NULL;
+
+	i2c_info->irq = intr + MRST_IRQ_OFFSET;
+	intr2nd_pdata = intr2nd + MRST_IRQ_OFFSET;
+
+	return &intr2nd_pdata;
+}
+
+static void __init *no_platform_data(void *info)
+{
+	return NULL;
+}
+
+static const struct devs_id __initconst device_ids[] = {
+	{"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data},
+	{"spi_max3111", SFI_DEV_TYPE_SPI, 0, &max3111_platform_data},
+	{"i2c_max7315", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
+	{"i2c_max7315_2", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
+	{"emc1403", SFI_DEV_TYPE_I2C, 1, &emc1403_platform_data},
+	{"i2c_accel", SFI_DEV_TYPE_I2C, 0, &lis331dl_platform_data},
+	{"pmic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data},
+	{"msic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data},
+	{},
+};
+
+#define MAX_IPCDEVS	24
+static struct platform_device *ipc_devs[MAX_IPCDEVS];
+static int ipc_next_dev;
+
+#define MAX_SCU_SPI	24
+static struct spi_board_info *spi_devs[MAX_SCU_SPI];
+static int spi_next_dev;
+
+#define MAX_SCU_I2C	24
+static struct i2c_board_info *i2c_devs[MAX_SCU_I2C];
+static int i2c_bus[MAX_SCU_I2C];
+static int i2c_next_dev;
+
+static void __init intel_scu_device_register(struct platform_device *pdev)
+{
+	if(ipc_next_dev == MAX_IPCDEVS)
+		pr_err("too many SCU IPC devices");
+	else
+		ipc_devs[ipc_next_dev++] = pdev;
+}
+
+static void __init intel_scu_spi_device_register(struct spi_board_info *sdev)
+{
+	struct spi_board_info *new_dev;
+
+	if (spi_next_dev == MAX_SCU_SPI) {
+		pr_err("too many SCU SPI devices");
+		return;
+	}
+
+	new_dev = kzalloc(sizeof(*sdev), GFP_KERNEL);
+	if (!new_dev) {
+		pr_err("failed to alloc mem for delayed spi dev %s\n",
+			sdev->modalias);
+		return;
+	}
+	memcpy(new_dev, sdev, sizeof(*sdev));
+
+	spi_devs[spi_next_dev++] = new_dev;
+}
+
+static void __init intel_scu_i2c_device_register(int bus,
+						struct i2c_board_info *idev)
+{
+	struct i2c_board_info *new_dev;
+
+	if (i2c_next_dev == MAX_SCU_I2C) {
+		pr_err("too many SCU I2C devices");
+		return;
+	}
+
+	new_dev = kzalloc(sizeof(*idev), GFP_KERNEL);
+	if (!new_dev) {
+		pr_err("failed to alloc mem for delayed i2c dev %s\n",
+			idev->type);
+		return;
+	}
+	memcpy(new_dev, idev, sizeof(*idev));
+
+	i2c_bus[i2c_next_dev] = bus;
+	i2c_devs[i2c_next_dev++] = new_dev;
+}
+
+/* Called by IPC driver */
+void intel_scu_devices_create(void)
+{
+	int i;
+
+	for (i = 0; i < ipc_next_dev; i++)
+		platform_device_add(ipc_devs[i]);
+
+	for (i = 0; i < spi_next_dev; i++)
+		spi_register_board_info(spi_devs[i], 1);
+
+	for (i = 0; i < i2c_next_dev; i++) {
+		struct i2c_adapter *adapter;
+		struct i2c_client *client;
+
+		adapter = i2c_get_adapter(i2c_bus[i]);
+		if (adapter) {
+			client = i2c_new_device(adapter, i2c_devs[i]);
+			if (!client)
+				pr_err("can't create i2c device %s\n",
+					i2c_devs[i]->type);
+		} else
+			i2c_register_board_info(i2c_bus[i], i2c_devs[i], 1);
+	}
+}
+EXPORT_SYMBOL_GPL(intel_scu_devices_create);
+
+/* Called by IPC driver */
+void intel_scu_devices_destroy(void)
+{
+	int i;
+
+	for (i = 0; i < ipc_next_dev; i++)
+		platform_device_del(ipc_devs[i]);
+}
+EXPORT_SYMBOL_GPL(intel_scu_devices_destroy);
+
+static void __init install_irq_resource(struct platform_device *pdev, int irq)
+{
+	/* Single threaded */
+	static struct resource __initdata res = {
+		.name = "IRQ",
+		.flags = IORESOURCE_IRQ,
+	};
+	res.start = irq;
+	platform_device_add_resources(pdev, &res, 1);
+}
+
+static void __init sfi_handle_ipc_dev(struct platform_device *pdev)
+{
+	const struct devs_id *dev = device_ids;
+	void *pdata = NULL;
+
+	while (dev->name[0]) {
+		if (dev->type == SFI_DEV_TYPE_IPC &&
+			!strncmp(dev->name, pdev->name, SFI_NAME_LEN)) {
+			pdata = dev->get_platform_data(pdev);
+			break;
+		}
+		dev++;
+	}
+	pdev->dev.platform_data = pdata;
+	intel_scu_device_register(pdev);
+}
+
+static void __init sfi_handle_spi_dev(struct spi_board_info *spi_info)
+{
+	const struct devs_id *dev = device_ids;
+	void *pdata = NULL;
+
+	while (dev->name[0]) {
+		if (dev->type == SFI_DEV_TYPE_SPI &&
+				!strncmp(dev->name, spi_info->modalias, SFI_NAME_LEN)) {
+			pdata = dev->get_platform_data(spi_info);
+			break;
+		}
+		dev++;
+	}
+	spi_info->platform_data = pdata;
+	if (dev->delay)
+		intel_scu_spi_device_register(spi_info);
+	else
+		spi_register_board_info(spi_info, 1);
+}
+
+static void __init sfi_handle_i2c_dev(int bus, struct i2c_board_info *i2c_info)
+{
+	const struct devs_id *dev = device_ids;
+	void *pdata = NULL;
+
+	while (dev->name[0]) {
+		if (dev->type == SFI_DEV_TYPE_I2C &&
+			!strncmp(dev->name, i2c_info->type, SFI_NAME_LEN)) {
+			pdata = dev->get_platform_data(i2c_info);
+			break;
+		}
+		dev++;
+	}
+	i2c_info->platform_data = pdata;
+
+	if (dev->delay)
+		intel_scu_i2c_device_register(bus, i2c_info);
+	else
+		i2c_register_board_info(bus, i2c_info, 1);
+ }
+
+
+static int __init sfi_parse_devs(struct sfi_table_header *table)
+{
+	struct sfi_table_simple *sb;
+	struct sfi_device_table_entry *pentry;
+	struct spi_board_info spi_info;
+	struct i2c_board_info i2c_info;
+	struct platform_device *pdev;
+	int num, i, bus;
+	int ioapic;
+	struct io_apic_irq_attr irq_attr;
+
+	sb = (struct sfi_table_simple *)table;
+	num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry);
+	pentry = (struct sfi_device_table_entry *)sb->pentry;
+
+	for (i = 0; i < num; i++, pentry++) {
+		if (pentry->irq != (u8)0xff) { /* native RTE case */
+			/* these SPI2 devices are not exposed to system as PCI
+			 * devices, but they have separate RTE entry in IOAPIC
+			 * so we have to enable them one by one here
+			 */
+			ioapic = mp_find_ioapic(pentry->irq);
+			irq_attr.ioapic = ioapic;
+			irq_attr.ioapic_pin = pentry->irq;
+			irq_attr.trigger = 1;
+			irq_attr.polarity = 1;
+			io_apic_set_pci_routing(NULL, pentry->irq, &irq_attr);
+		}
+		switch (pentry->type) {
+		case SFI_DEV_TYPE_IPC:
+			/* ID as IRQ is a hack that will go away */
+			pdev = platform_device_alloc(pentry->name, pentry->irq);
+			if (pdev == NULL) {
+				pr_err("out of memory for SFI platform device '%s'.\n",
+							pentry->name);
+				continue;
+			}
+			install_irq_resource(pdev, pentry->irq);
+			pr_debug("info[%2d]: IPC bus, name = %16.16s, "
+				"irq = 0x%2x\n", i, pentry->name, pentry->irq);
+			sfi_handle_ipc_dev(pdev);
+			break;
+		case SFI_DEV_TYPE_SPI:
+			memset(&spi_info, 0, sizeof(spi_info));
+			strncpy(spi_info.modalias, pentry->name, SFI_NAME_LEN);
+			spi_info.irq = pentry->irq;
+			spi_info.bus_num = pentry->host_num;
+			spi_info.chip_select = pentry->addr;
+			spi_info.max_speed_hz = pentry->max_freq;
+			pr_debug("info[%2d]: SPI bus = %d, name = %16.16s, "
+				"irq = 0x%2x, max_freq = %d, cs = %d\n", i,
+				spi_info.bus_num,
+				spi_info.modalias,
+				spi_info.irq,
+				spi_info.max_speed_hz,
+				spi_info.chip_select);
+			sfi_handle_spi_dev(&spi_info);
+			break;
+		case SFI_DEV_TYPE_I2C:
+			memset(&i2c_info, 0, sizeof(i2c_info));
+			bus = pentry->host_num;
+			strncpy(i2c_info.type, pentry->name, SFI_NAME_LEN);
+			i2c_info.irq = pentry->irq;
+			i2c_info.addr = pentry->addr;
+			pr_debug("info[%2d]: I2C bus = %d, name = %16.16s, "
+				"irq = 0x%2x, addr = 0x%x\n", i, bus,
+				i2c_info.type,
+				i2c_info.irq,
+				i2c_info.addr);
+			sfi_handle_i2c_dev(bus, &i2c_info);
+			break;
+		case SFI_DEV_TYPE_UART:
+		case SFI_DEV_TYPE_HSI:
+		default:
+			;
+		}
+	}
+	return 0;
+}
+
+static int __init mrst_platform_init(void)
+{
+	sfi_table_parse(SFI_SIG_GPIO, NULL, NULL, sfi_parse_gpio);
+	sfi_table_parse(SFI_SIG_DEVS, NULL, NULL, sfi_parse_devs);
+	return 0;
+}
+arch_initcall(mrst_platform_init);
+
+/*
+ * we will search these buttons in SFI GPIO table (by name)
+ * and register them dynamically. Please add all possible
+ * buttons here, we will shrink them if no GPIO found.
+ */
+static struct gpio_keys_button gpio_button[] = {
+	{KEY_POWER,		-1, 1, "power_btn",	EV_KEY, 0, 3000},
+	{KEY_PROG1,		-1, 1, "prog_btn1",	EV_KEY, 0, 20},
+	{KEY_PROG2,		-1, 1, "prog_btn2",	EV_KEY, 0, 20},
+	{SW_LID,		-1, 1, "lid_switch",	EV_SW,  0, 20},
+	{KEY_VOLUMEUP,		-1, 1, "vol_up",	EV_KEY, 0, 20},
+	{KEY_VOLUMEDOWN,	-1, 1, "vol_down",	EV_KEY, 0, 20},
+	{KEY_CAMERA,		-1, 1, "camera_full",	EV_KEY, 0, 20},
+	{KEY_CAMERA_FOCUS,	-1, 1, "camera_half",	EV_KEY, 0, 20},
+	{SW_KEYPAD_SLIDE,	-1, 1, "MagSw1",	EV_SW,  0, 20},
+	{SW_KEYPAD_SLIDE,	-1, 1, "MagSw2",	EV_SW,  0, 20},
+};
+
+static struct gpio_keys_platform_data mrst_gpio_keys = {
+	.buttons	= gpio_button,
+	.rep		= 1,
+	.nbuttons	= -1, /* will fill it after search */
+};
+
+static struct platform_device pb_device = {
+	.name		= "gpio-keys",
+	.id		= -1,
+	.dev		= {
+		.platform_data	= &mrst_gpio_keys,
+	},
+};
+
+/*
+ * Shrink the non-existent buttons, register the gpio button
+ * device if there is some
+ */
+static int __init pb_keys_init(void)
+{
+	struct gpio_keys_button *gb = gpio_button;
+	int i, num, good = 0;
+
+	num = sizeof(gpio_button) / sizeof(struct gpio_keys_button);
+	for (i = 0; i < num; i++) {
+		gb[i].gpio = get_gpio_by_name(gb[i].desc);
+		if (gb[i].gpio == -1)
+			continue;
+
+		if (i != good)
+			gb[good] = gb[i];
+		good++;
+	}
+
+	if (good) {
+		mrst_gpio_keys.nbuttons = good;
+		return platform_device_register(&pb_device);
+	}
+	return 0;
+}
+late_initcall(pb_keys_init);

arch/x86/platform/mrst/vrtc.c

@@ -0,0 +1,165 @@
+/*
+ * vrtc.c: Driver for virtual RTC device on Intel MID platform
+ *
+ * (C) Copyright 2009 Intel Corporation
+ *
+ * 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; version 2
+ * of the License.
+ *
+ * Note:
+ * VRTC is emulated by system controller firmware, the real HW
+ * RTC is located in the PMIC device. SCU FW shadows PMIC RTC
+ * in a memory mapped IO space that is visible to the host IA
+ * processor.
+ *
+ * This driver is based on RTC CMOS driver.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/sfi.h>
+#include <linux/platform_device.h>
+
+#include <asm/mrst.h>
+#include <asm/mrst-vrtc.h>
+#include <asm/time.h>
+#include <asm/fixmap.h>
+
+static unsigned char __iomem *vrtc_virt_base;
+
+unsigned char vrtc_cmos_read(unsigned char reg)
+{
+	unsigned char retval;
+
+	/* vRTC's registers range from 0x0 to 0xD */
+	if (reg > 0xd || !vrtc_virt_base)
+		return 0xff;
+
+	lock_cmos_prefix(reg);
+	retval = __raw_readb(vrtc_virt_base + (reg << 2));
+	lock_cmos_suffix(reg);
+	return retval;
+}
+EXPORT_SYMBOL_GPL(vrtc_cmos_read);
+
+void vrtc_cmos_write(unsigned char val, unsigned char reg)
+{
+	if (reg > 0xd || !vrtc_virt_base)
+		return;
+
+	lock_cmos_prefix(reg);
+	__raw_writeb(val, vrtc_virt_base + (reg << 2));
+	lock_cmos_suffix(reg);
+}
+EXPORT_SYMBOL_GPL(vrtc_cmos_write);
+
+unsigned long vrtc_get_time(void)
+{
+	u8 sec, min, hour, mday, mon;
+	u32 year;
+
+	while ((vrtc_cmos_read(RTC_FREQ_SELECT) & RTC_UIP))
+		cpu_relax();
+
+	sec = vrtc_cmos_read(RTC_SECONDS);
+	min = vrtc_cmos_read(RTC_MINUTES);
+	hour = vrtc_cmos_read(RTC_HOURS);
+	mday = vrtc_cmos_read(RTC_DAY_OF_MONTH);
+	mon = vrtc_cmos_read(RTC_MONTH);
+	year = vrtc_cmos_read(RTC_YEAR);
+
+	/* vRTC YEAR reg contains the offset to 1960 */
+	year += 1960;
+
+	printk(KERN_INFO "vRTC: sec: %d min: %d hour: %d day: %d "
+		"mon: %d year: %d\n", sec, min, hour, mday, mon, year);
+
+	return mktime(year, mon, mday, hour, min, sec);
+}
+
+/* Only care about the minutes and seconds */
+int vrtc_set_mmss(unsigned long nowtime)
+{
+	int real_sec, real_min;
+	int vrtc_min;
+
+	vrtc_min = vrtc_cmos_read(RTC_MINUTES);
+
+	real_sec = nowtime % 60;
+	real_min = nowtime / 60;
+	if (((abs(real_min - vrtc_min) + 15)/30) & 1)
+		real_min += 30;
+	real_min %= 60;
+
+	vrtc_cmos_write(real_sec, RTC_SECONDS);
+	vrtc_cmos_write(real_min, RTC_MINUTES);
+	return 0;
+}
+
+void __init mrst_rtc_init(void)
+{
+	unsigned long rtc_paddr;
+	void __iomem *virt_base;
+
+	sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc);
+	if (!sfi_mrtc_num)
+		return;
+
+	rtc_paddr = sfi_mrtc_array[0].phys_addr;
+
+	/* vRTC's register address may not be page aligned */
+	set_fixmap_nocache(FIX_LNW_VRTC, rtc_paddr);
+
+	virt_base = (void __iomem *)__fix_to_virt(FIX_LNW_VRTC);
+	virt_base += rtc_paddr & ~PAGE_MASK;
+	vrtc_virt_base = virt_base;
+
+	x86_platform.get_wallclock = vrtc_get_time;
+	x86_platform.set_wallclock = vrtc_set_mmss;
+}
+
+/*
+ * The Moorestown platform has a memory mapped virtual RTC device that emulates
+ * the programming interface of the RTC.
+ */
+
+static struct resource vrtc_resources[] = {
+	[0] = {
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.flags	= IORESOURCE_IRQ,
+	}
+};
+
+static struct platform_device vrtc_device = {
+	.name		= "rtc_mrst",
+	.id		= -1,
+	.resource	= vrtc_resources,
+	.num_resources	= ARRAY_SIZE(vrtc_resources),
+};
+
+/* Register the RTC device if appropriate */
+static int __init mrst_device_create(void)
+{
+	/* No Moorestown, no device */
+	if (!mrst_identify_cpu())
+		return -ENODEV;
+	/* No timer, no device */
+	if (!sfi_mrtc_num)
+		return -ENODEV;
+
+	/* iomem resource */
+	vrtc_resources[0].start = sfi_mrtc_array[0].phys_addr;
+	vrtc_resources[0].end = sfi_mrtc_array[0].phys_addr +
+				MRST_VRTC_MAP_SZ;
+	/* irq resource */
+	vrtc_resources[1].start = sfi_mrtc_array[0].irq;
+	vrtc_resources[1].end = sfi_mrtc_array[0].irq;
+
+	return platform_device_register(&vrtc_device);
+}
+
+module_init(mrst_device_create);

arch/x86/platform/sfi/sfi.c

@@ -48,9 +48,9 @@ static void __init mp_sfi_register_lapic_address(unsigned long address)
 /* All CPUs enumerated by SFI must be present and enabled */
 static void __cpuinit mp_sfi_register_lapic(u8 id)
 {
-	if (MAX_APICS - id <= 0) {
+	if (MAX_LOCAL_APIC - id <= 0) {
 		pr_warning("Processor #%d invalid (max %d)\n",
-			id, MAX_APICS);
+			id, MAX_LOCAL_APIC);
 		return;
 	}
 

arch/x86/platform/uv/tlb_uv.c

@@ -1341,7 +1341,7 @@ uv_activation_descriptor_init(int node, int pnode)
 
 	/*
 	 * each bau_desc is 64 bytes; there are 8 (UV_ITEMS_PER_DESCRIPTOR)
-	 * per cpu; and up to 32 (UV_ADP_SIZE) cpu's per uvhub
+	 * per cpu; and one per cpu on the uvhub (UV_ADP_SIZE)
 	 */
 	bau_desc = kmalloc_node(sizeof(struct bau_desc) * UV_ADP_SIZE
 				* UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node);
@@ -1490,7 +1490,7 @@ calculate_destination_timeout(void)
 /*
  * initialize the bau_control structure for each cpu
  */
-static void __init uv_init_per_cpu(int nuvhubs)
+static int __init uv_init_per_cpu(int nuvhubs)
 {
 	int i;
 	int cpu;
@@ -1507,7 +1507,7 @@ static void __init uv_init_per_cpu(int nuvhubs)
 	struct bau_control *smaster = NULL;
 	struct socket_desc {
 		short num_cpus;
-		short cpu_number[16];
+		short cpu_number[MAX_CPUS_PER_SOCKET];
 	};
 	struct uvhub_desc {
 		unsigned short socket_mask;
@@ -1540,6 +1540,10 @@ static void __init uv_init_per_cpu(int nuvhubs)
 		sdp = &bdp->socket[socket];
 		sdp->cpu_number[sdp->num_cpus] = cpu;
 		sdp->num_cpus++;
+		if (sdp->num_cpus > MAX_CPUS_PER_SOCKET) {
+			printk(KERN_EMERG "%d cpus per socket invalid\n", sdp->num_cpus);
+			return 1;
+		}
 	}
 	for (uvhub = 0; uvhub < nuvhubs; uvhub++) {
 		if (!(*(uvhub_mask + (uvhub/8)) & (1 << (uvhub%8))))
@@ -1570,6 +1574,12 @@ static void __init uv_init_per_cpu(int nuvhubs)
 				bcp->uvhub_master = hmaster;
 				bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->
 						blade_processor_id;
+				if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
+					printk(KERN_EMERG
+						"%d cpus per uvhub invalid\n",
+						bcp->uvhub_cpu);
+					return 1;
+				}
 			}
 nextsocket:
 			socket++;
@@ -1595,6 +1605,7 @@ nextsocket:
 		bcp->congested_reps = congested_reps;
 		bcp->congested_period = congested_period;
 	}
+	return 0;
 }
 
 /*
@@ -1625,7 +1636,10 @@ static int __init uv_bau_init(void)
 	spin_lock_init(&disable_lock);
 	congested_cycles = microsec_2_cycles(congested_response_us);
 
-	uv_init_per_cpu(nuvhubs);
+	if (uv_init_per_cpu(nuvhubs)) {
+		nobau = 1;
+		return 0;
+	}
 
 	uv_partition_base_pnode = 0x7fffffff;
 	for (uvhub = 0; uvhub < nuvhubs; uvhub++)

arch/x86/platform/visws/visws_quirks.c

@@ -171,7 +171,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 	ver = m->apicver;
 	if ((ver >= 0x14 && m->apicid >= 0xff) || m->apicid >= 0xf) {
 		printk(KERN_ERR "Processor #%d INVALID. (Max ID: %d).\n",
-			m->apicid, MAX_APICS);
+			m->apicid, MAX_LOCAL_APIC);
 		return;
 	}
 

drivers/acpi/numa.c

@@ -275,13 +275,23 @@ acpi_table_parse_srat(enum acpi_srat_type id,
 int __init acpi_numa_init(void)
 {
 	int ret = 0;
+	int nr_cpu_entries = nr_cpu_ids;
+
+#ifdef CONFIG_X86
+	/*
+	 * Should not limit number with cpu num that is from NR_CPUS or nr_cpus=
+	 * SRAT cpu entries could have different order with that in MADT.
+	 * So go over all cpu entries in SRAT to get apicid to node mapping.
+	 */
+	nr_cpu_entries = MAX_LOCAL_APIC;
+#endif
 
 	/* SRAT: Static Resource Affinity Table */
 	if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
 		acpi_table_parse_srat(ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY,
-				     acpi_parse_x2apic_affinity, nr_cpu_ids);
+				     acpi_parse_x2apic_affinity, nr_cpu_entries);
 		acpi_table_parse_srat(ACPI_SRAT_TYPE_CPU_AFFINITY,
-				     acpi_parse_processor_affinity, nr_cpu_ids);
+				     acpi_parse_processor_affinity, nr_cpu_entries);
 		ret = acpi_table_parse_srat(ACPI_SRAT_TYPE_MEMORY_AFFINITY,
 					    acpi_parse_memory_affinity,
 					    NR_NODE_MEMBLKS);

drivers/char/agp/amd64-agp.c

@@ -38,7 +38,7 @@ static int agp_bridges_found;
 
 static void amd64_tlbflush(struct agp_memory *temp)
 {
-	k8_flush_garts();
+	amd_flush_garts();
 }
 
 static int amd64_insert_memory(struct agp_memory *mem, off_t pg_start, int type)
@@ -124,7 +124,7 @@ static int amd64_fetch_size(void)
 	u32 temp;
 	struct aper_size_info_32 *values;
 
-	dev = k8_northbridges.nb_misc[0];
+	dev = node_to_amd_nb(0)->misc;
 	if (dev==NULL)
 		return 0;
 
@@ -181,16 +181,15 @@ static int amd_8151_configure(void)
 	unsigned long gatt_bus = virt_to_phys(agp_bridge->gatt_table_real);
 	int i;
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return 0;
 
 	/* Configure AGP regs in each x86-64 host bridge. */
-	for (i = 0; i < k8_northbridges.num; i++) {
+	for (i = 0; i < amd_nb_num(); i++) {
 		agp_bridge->gart_bus_addr =
-				amd64_configure(k8_northbridges.nb_misc[i],
-						gatt_bus);
+			amd64_configure(node_to_amd_nb(i)->misc, gatt_bus);
 	}
-	k8_flush_garts();
+	amd_flush_garts();
 	return 0;
 }
 
@@ -200,11 +199,11 @@ static void amd64_cleanup(void)
 	u32 tmp;
 	int i;
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return;
 
-	for (i = 0; i < k8_northbridges.num; i++) {
-		struct pci_dev *dev = k8_northbridges.nb_misc[i];
+	for (i = 0; i < amd_nb_num(); i++) {
+		struct pci_dev *dev = node_to_amd_nb(i)->misc;
 		/* disable gart translation */
 		pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &tmp);
 		tmp &= ~GARTEN;
@@ -331,15 +330,15 @@ static __devinit int cache_nbs(struct pci_dev *pdev, u32 cap_ptr)
 {
 	int i;
 
-	if (cache_k8_northbridges() < 0)
+	if (amd_cache_northbridges() < 0)
 		return -ENODEV;
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return -ENODEV;
 
 	i = 0;
-	for (i = 0; i < k8_northbridges.num; i++) {
-		struct pci_dev *dev = k8_northbridges.nb_misc[i];
+	for (i = 0; i < amd_nb_num(); i++) {
+		struct pci_dev *dev = node_to_amd_nb(i)->misc;
 		if (fix_northbridge(dev, pdev, cap_ptr) < 0) {
 			dev_err(&dev->dev, "no usable aperture found\n");
 #ifdef __x86_64__
@@ -416,7 +415,7 @@ static int __devinit uli_agp_init(struct pci_dev *pdev)
 	}
 
 	/* shadow x86-64 registers into ULi registers */
-	pci_read_config_dword (k8_northbridges.nb_misc[0], AMD64_GARTAPERTUREBASE,
+	pci_read_config_dword (node_to_amd_nb(0)->misc, AMD64_GARTAPERTUREBASE,
 			       &httfea);
 
 	/* if x86-64 aperture base is beyond 4G, exit here */
@@ -484,7 +483,7 @@ static int nforce3_agp_init(struct pci_dev *pdev)
 	pci_write_config_dword(dev1, NVIDIA_X86_64_1_APSIZE, tmp);
 
 	/* shadow x86-64 registers into NVIDIA registers */
-	pci_read_config_dword (k8_northbridges.nb_misc[0], AMD64_GARTAPERTUREBASE,
+	pci_read_config_dword (node_to_amd_nb(0)->misc, AMD64_GARTAPERTUREBASE,
 			       &apbase);
 
 	/* if x86-64 aperture base is beyond 4G, exit here */
@@ -778,7 +777,7 @@ int __init agp_amd64_init(void)
 		}
 
 		/* First check that we have at least one AMD64 NB */
-		if (!pci_dev_present(k8_nb_ids))
+		if (!pci_dev_present(amd_nb_misc_ids))
 			return -ENODEV;
 
 		/* Look for any AGP bridge */

drivers/edac/amd64_edac.c

@@ -2917,7 +2917,7 @@ static int __init amd64_edac_init(void)
 
 	opstate_init();
 
-	if (cache_k8_northbridges() < 0)
+	if (amd_cache_northbridges() < 0)
 		goto err_ret;
 
 	msrs = msrs_alloc();
@@ -2934,7 +2934,7 @@ static int __init amd64_edac_init(void)
 	 * to finish initialization of the MC instances.
 	 */
 	err = -ENODEV;
-	for (nb = 0; nb < k8_northbridges.num; nb++) {
+	for (nb = 0; nb < amd_nb_num(); nb++) {
 		if (!pvt_lookup[nb])
 			continue;
 

drivers/platform/x86/intel_scu_ipc.c

@@ -26,6 +26,7 @@
 #include <linux/sfi.h>
 #include <asm/mrst.h>
 #include <asm/intel_scu_ipc.h>
+#include <asm/mrst.h>
 
 /* IPC defines the following message types */
 #define IPCMSG_WATCHDOG_TIMER 0xF8 /* Set Kernel Watchdog Threshold */
@@ -699,6 +700,9 @@ static int ipc_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		iounmap(ipcdev.ipc_base);
 		return -ENOMEM;
 	}
+
+	intel_scu_devices_create();
+
 	return 0;
 }
 
@@ -720,6 +724,7 @@ static void ipc_remove(struct pci_dev *pdev)
 	iounmap(ipcdev.ipc_base);
 	iounmap(ipcdev.i2c_base);
 	ipcdev.pdev = NULL;
+	intel_scu_devices_destroy();
 }
 
 static const struct pci_device_id pci_ids[] = {

drivers/rtc/Kconfig

@@ -463,6 +463,18 @@ config RTC_DRV_CMOS
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-cmos.
 
+config RTC_DRV_VRTC
+	tristate "Virtual RTC for Moorestown platforms"
+	depends on X86_MRST
+	default y if X86_MRST
+
+	help
+	Say "yes" here to get direct support for the real time clock
+	found on Moorestown platforms. The VRTC is a emulated RTC that
+	derives its clock source from a real RTC in the PMIC. The MC146818
+	style programming interface is mostly conserved, but any
+	updates are done via IPC calls to the system controller FW.
+
 config RTC_DRV_DS1216
 	tristate "Dallas DS1216"
 	depends on SNI_RM

drivers/rtc/Makefile

@@ -30,6 +30,7 @@ obj-$(CONFIG_RTC_DRV_CMOS)	+= rtc-cmos.o
 obj-$(CONFIG_RTC_DRV_COH901331)	+= rtc-coh901331.o
 obj-$(CONFIG_RTC_DRV_DAVINCI)	+= rtc-davinci.o
 obj-$(CONFIG_RTC_DRV_DM355EVM)	+= rtc-dm355evm.o
+obj-$(CONFIG_RTC_DRV_VRTC)	+= rtc-mrst.o
 obj-$(CONFIG_RTC_DRV_DS1216)	+= rtc-ds1216.o
 obj-$(CONFIG_RTC_DRV_DS1286)	+= rtc-ds1286.o
 obj-$(CONFIG_RTC_DRV_DS1302)	+= rtc-ds1302.o

drivers/rtc/rtc-mrst.c

@@ -0,0 +1,582 @@
+/*
+ * rtc-mrst.c: Driver for Moorestown virtual RTC
+ *
+ * (C) Copyright 2009 Intel Corporation
+ * Author: Jacob Pan (jacob.jun.pan@intel.com)
+ *	   Feng Tang (feng.tang@intel.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; version 2
+ * of the License.
+ *
+ * Note:
+ * VRTC is emulated by system controller firmware, the real HW
+ * RTC is located in the PMIC device. SCU FW shadows PMIC RTC
+ * in a memory mapped IO space that is visible to the host IA
+ * processor.
+ *
+ * This driver is based upon drivers/rtc/rtc-cmos.c
+ */
+
+/*
+ * Note:
+ *  * vRTC only supports binary mode and 24H mode
+ *  * vRTC only support PIE and AIE, no UIE, and its PIE only happens
+ *    at 23:59:59pm everyday, no support for adjustable frequency
+ *  * Alarm function is also limited to hr/min/sec.
+ */
+
+#include <linux/mod_devicetable.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sfi.h>
+
+#include <asm-generic/rtc.h>
+#include <asm/intel_scu_ipc.h>
+#include <asm/mrst.h>
+#include <asm/mrst-vrtc.h>
+
+struct mrst_rtc {
+	struct rtc_device	*rtc;
+	struct device		*dev;
+	int			irq;
+	struct resource		*iomem;
+
+	u8			enabled_wake;
+	u8			suspend_ctrl;
+};
+
+static const char driver_name[] = "rtc_mrst";
+
+#define	RTC_IRQMASK	(RTC_PF | RTC_AF)
+
+static inline int is_intr(u8 rtc_intr)
+{
+	if (!(rtc_intr & RTC_IRQF))
+		return 0;
+	return rtc_intr & RTC_IRQMASK;
+}
+
+/*
+ * rtc_time's year contains the increment over 1900, but vRTC's YEAR
+ * register can't be programmed to value larger than 0x64, so vRTC
+ * driver chose to use 1960 (1970 is UNIX time start point) as the base,
+ * and does the translation at read/write time.
+ *
+ * Why not just use 1970 as the offset? it's because using 1960 will
+ * make it consistent in leap year setting for both vrtc and low-level
+ * physical rtc devices.
+ */
+static int mrst_read_time(struct device *dev, struct rtc_time *time)
+{
+	unsigned long flags;
+
+	if (rtc_is_updating())
+		mdelay(20);
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	time->tm_sec = vrtc_cmos_read(RTC_SECONDS);
+	time->tm_min = vrtc_cmos_read(RTC_MINUTES);
+	time->tm_hour = vrtc_cmos_read(RTC_HOURS);
+	time->tm_mday = vrtc_cmos_read(RTC_DAY_OF_MONTH);
+	time->tm_mon = vrtc_cmos_read(RTC_MONTH);
+	time->tm_year = vrtc_cmos_read(RTC_YEAR);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
+	/* Adjust for the 1960/1900 */
+	time->tm_year += 60;
+	time->tm_mon--;
+	return RTC_24H;
+}
+
+static int mrst_set_time(struct device *dev, struct rtc_time *time)
+{
+	int ret;
+	unsigned long flags;
+	unsigned char mon, day, hrs, min, sec;
+	unsigned int yrs;
+
+	yrs = time->tm_year;
+	mon = time->tm_mon + 1;   /* tm_mon starts at zero */
+	day = time->tm_mday;
+	hrs = time->tm_hour;
+	min = time->tm_min;
+	sec = time->tm_sec;
+
+	if (yrs < 70 || yrs > 138)
+		return -EINVAL;
+	yrs -= 60;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+
+	vrtc_cmos_write(yrs, RTC_YEAR);
+	vrtc_cmos_write(mon, RTC_MONTH);
+	vrtc_cmos_write(day, RTC_DAY_OF_MONTH);
+	vrtc_cmos_write(hrs, RTC_HOURS);
+	vrtc_cmos_write(min, RTC_MINUTES);
+	vrtc_cmos_write(sec, RTC_SECONDS);
+
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
+	ret = intel_scu_ipc_simple_command(IPCMSG_VRTC, IPC_CMD_VRTC_SETTIME);
+	return ret;
+}
+
+static int mrst_read_alarm(struct device *dev, struct rtc_wkalrm *t)
+{
+	struct mrst_rtc	*mrst = dev_get_drvdata(dev);
+	unsigned char rtc_control;
+
+	if (mrst->irq <= 0)
+		return -EIO;
+
+	/* Basic alarms only support hour, minute, and seconds fields.
+	 * Some also support day and month, for alarms up to a year in
+	 * the future.
+	 */
+	t->time.tm_mday = -1;
+	t->time.tm_mon = -1;
+	t->time.tm_year = -1;
+
+	/* vRTC only supports binary mode */
+	spin_lock_irq(&rtc_lock);
+	t->time.tm_sec = vrtc_cmos_read(RTC_SECONDS_ALARM);
+	t->time.tm_min = vrtc_cmos_read(RTC_MINUTES_ALARM);
+	t->time.tm_hour = vrtc_cmos_read(RTC_HOURS_ALARM);
+
+	rtc_control = vrtc_cmos_read(RTC_CONTROL);
+	spin_unlock_irq(&rtc_lock);
+
+	t->enabled = !!(rtc_control & RTC_AIE);
+	t->pending = 0;
+
+	return 0;
+}
+
+static void mrst_checkintr(struct mrst_rtc *mrst, unsigned char rtc_control)
+{
+	unsigned char	rtc_intr;
+
+	/*
+	 * NOTE after changing RTC_xIE bits we always read INTR_FLAGS;
+	 * allegedly some older rtcs need that to handle irqs properly
+	 */
+	rtc_intr = vrtc_cmos_read(RTC_INTR_FLAGS);
+	rtc_intr &= (rtc_control & RTC_IRQMASK) | RTC_IRQF;
+	if (is_intr(rtc_intr))
+		rtc_update_irq(mrst->rtc, 1, rtc_intr);
+}
+
+static void mrst_irq_enable(struct mrst_rtc *mrst, unsigned char mask)
+{
+	unsigned char	rtc_control;
+
+	/*
+	 * Flush any pending IRQ status, notably for update irqs,
+	 * before we enable new IRQs
+	 */
+	rtc_control = vrtc_cmos_read(RTC_CONTROL);
+	mrst_checkintr(mrst, rtc_control);
+
+	rtc_control |= mask;
+	vrtc_cmos_write(rtc_control, RTC_CONTROL);
+
+	mrst_checkintr(mrst, rtc_control);
+}
+
+static void mrst_irq_disable(struct mrst_rtc *mrst, unsigned char mask)
+{
+	unsigned char	rtc_control;
+
+	rtc_control = vrtc_cmos_read(RTC_CONTROL);
+	rtc_control &= ~mask;
+	vrtc_cmos_write(rtc_control, RTC_CONTROL);
+	mrst_checkintr(mrst, rtc_control);
+}
+
+static int mrst_set_alarm(struct device *dev, struct rtc_wkalrm *t)
+{
+	struct mrst_rtc	*mrst = dev_get_drvdata(dev);
+	unsigned char hrs, min, sec;
+	int ret = 0;
+
+	if (!mrst->irq)
+		return -EIO;
+
+	hrs = t->time.tm_hour;
+	min = t->time.tm_min;
+	sec = t->time.tm_sec;
+
+	spin_lock_irq(&rtc_lock);
+	/* Next rtc irq must not be from previous alarm setting */
+	mrst_irq_disable(mrst, RTC_AIE);
+
+	/* Update alarm */
+	vrtc_cmos_write(hrs, RTC_HOURS_ALARM);
+	vrtc_cmos_write(min, RTC_MINUTES_ALARM);
+	vrtc_cmos_write(sec, RTC_SECONDS_ALARM);
+
+	spin_unlock_irq(&rtc_lock);
+
+	ret = intel_scu_ipc_simple_command(IPCMSG_VRTC, IPC_CMD_VRTC_SETALARM);
+	if (ret)
+		return ret;
+
+	spin_lock_irq(&rtc_lock);
+	if (t->enabled)
+		mrst_irq_enable(mrst, RTC_AIE);
+
+	spin_unlock_irq(&rtc_lock);
+
+	return 0;
+}
+
+static int mrst_irq_set_state(struct device *dev, int enabled)
+{
+	struct mrst_rtc	*mrst = dev_get_drvdata(dev);
+	unsigned long	flags;
+
+	if (!mrst->irq)
+		return -ENXIO;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+
+	if (enabled)
+		mrst_irq_enable(mrst, RTC_PIE);
+	else
+		mrst_irq_disable(mrst, RTC_PIE);
+
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return 0;
+}
+
+#if defined(CONFIG_RTC_INTF_DEV) || defined(CONFIG_RTC_INTF_DEV_MODULE)
+
+/* Currently, the vRTC doesn't support UIE ON/OFF */
+static int
+mrst_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+{
+	struct mrst_rtc	*mrst = dev_get_drvdata(dev);
+	unsigned long	flags;
+
+	switch (cmd) {
+	case RTC_AIE_OFF:
+	case RTC_AIE_ON:
+		if (!mrst->irq)
+			return -EINVAL;
+		break;
+	default:
+		/* PIE ON/OFF is handled by mrst_irq_set_state() */
+		return -ENOIOCTLCMD;
+	}
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	switch (cmd) {
+	case RTC_AIE_OFF:	/* alarm off */
+		mrst_irq_disable(mrst, RTC_AIE);
+		break;
+	case RTC_AIE_ON:	/* alarm on */
+		mrst_irq_enable(mrst, RTC_AIE);
+		break;
+	}
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return 0;
+}
+
+#else
+#define	mrst_rtc_ioctl	NULL
+#endif
+
+#if defined(CONFIG_RTC_INTF_PROC) || defined(CONFIG_RTC_INTF_PROC_MODULE)
+
+static int mrst_procfs(struct device *dev, struct seq_file *seq)
+{
+	unsigned char	rtc_control, valid;
+
+	spin_lock_irq(&rtc_lock);
+	rtc_control = vrtc_cmos_read(RTC_CONTROL);
+	valid = vrtc_cmos_read(RTC_VALID);
+	spin_unlock_irq(&rtc_lock);
+
+	return seq_printf(seq,
+			"periodic_IRQ\t: %s\n"
+			"alarm\t\t: %s\n"
+			"BCD\t\t: no\n"
+			"periodic_freq\t: daily (not adjustable)\n",
+			(rtc_control & RTC_PIE) ? "on" : "off",
+			(rtc_control & RTC_AIE) ? "on" : "off");
+}
+
+#else
+#define	mrst_procfs	NULL
+#endif
+
+static const struct rtc_class_ops mrst_rtc_ops = {
+	.ioctl		= mrst_rtc_ioctl,
+	.read_time	= mrst_read_time,
+	.set_time	= mrst_set_time,
+	.read_alarm	= mrst_read_alarm,
+	.set_alarm	= mrst_set_alarm,
+	.proc		= mrst_procfs,
+	.irq_set_state	= mrst_irq_set_state,
+};
+
+static struct mrst_rtc	mrst_rtc;
+
+/*
+ * When vRTC IRQ is captured by SCU FW, FW will clear the AIE bit in
+ * Reg B, so no need for this driver to clear it
+ */
+static irqreturn_t mrst_rtc_irq(int irq, void *p)
+{
+	u8 irqstat;
+
+	spin_lock(&rtc_lock);
+	/* This read will clear all IRQ flags inside Reg C */
+	irqstat = vrtc_cmos_read(RTC_INTR_FLAGS);
+	spin_unlock(&rtc_lock);
+
+	irqstat &= RTC_IRQMASK | RTC_IRQF;
+	if (is_intr(irqstat)) {
+		rtc_update_irq(p, 1, irqstat);
+		return IRQ_HANDLED;
+	}
+	return IRQ_NONE;
+}
+
+static int __init
+vrtc_mrst_do_probe(struct device *dev, struct resource *iomem, int rtc_irq)
+{
+	int retval = 0;
+	unsigned char rtc_control;
+
+	/* There can be only one ... */
+	if (mrst_rtc.dev)
+		return -EBUSY;
+
+	if (!iomem)
+		return -ENODEV;
+
+	iomem = request_mem_region(iomem->start,
+			iomem->end + 1 - iomem->start,
+			driver_name);
+	if (!iomem) {
+		dev_dbg(dev, "i/o mem already in use.\n");
+		return -EBUSY;
+	}
+
+	mrst_rtc.irq = rtc_irq;
+	mrst_rtc.iomem = iomem;
+
+	mrst_rtc.rtc = rtc_device_register(driver_name, dev,
+				&mrst_rtc_ops, THIS_MODULE);
+	if (IS_ERR(mrst_rtc.rtc)) {
+		retval = PTR_ERR(mrst_rtc.rtc);
+		goto cleanup0;
+	}
+
+	mrst_rtc.dev = dev;
+	dev_set_drvdata(dev, &mrst_rtc);
+	rename_region(iomem, dev_name(&mrst_rtc.rtc->dev));
+
+	spin_lock_irq(&rtc_lock);
+	mrst_irq_disable(&mrst_rtc, RTC_PIE | RTC_AIE);
+	rtc_control = vrtc_cmos_read(RTC_CONTROL);
+	spin_unlock_irq(&rtc_lock);
+
+	if (!(rtc_control & RTC_24H) || (rtc_control & (RTC_DM_BINARY)))
+		dev_dbg(dev, "TODO: support more than 24-hr BCD mode\n");
+
+	if (rtc_irq) {
+		retval = request_irq(rtc_irq, mrst_rtc_irq,
+				IRQF_DISABLED, dev_name(&mrst_rtc.rtc->dev),
+				mrst_rtc.rtc);
+		if (retval < 0) {
+			dev_dbg(dev, "IRQ %d is already in use, err %d\n",
+				rtc_irq, retval);
+			goto cleanup1;
+		}
+	}
+	dev_dbg(dev, "initialised\n");
+	return 0;
+
+cleanup1:
+	mrst_rtc.dev = NULL;
+	rtc_device_unregister(mrst_rtc.rtc);
+cleanup0:
+	release_region(iomem->start, iomem->end + 1 - iomem->start);
+	dev_err(dev, "rtc-mrst: unable to initialise\n");
+	return retval;
+}
+
+static void rtc_mrst_do_shutdown(void)
+{
+	spin_lock_irq(&rtc_lock);
+	mrst_irq_disable(&mrst_rtc, RTC_IRQMASK);
+	spin_unlock_irq(&rtc_lock);
+}
+
+static void __exit rtc_mrst_do_remove(struct device *dev)
+{
+	struct mrst_rtc	*mrst = dev_get_drvdata(dev);
+	struct resource *iomem;
+
+	rtc_mrst_do_shutdown();
+
+	if (mrst->irq)
+		free_irq(mrst->irq, mrst->rtc);
+
+	rtc_device_unregister(mrst->rtc);
+	mrst->rtc = NULL;
+
+	iomem = mrst->iomem;
+	release_region(iomem->start, iomem->end + 1 - iomem->start);
+	mrst->iomem = NULL;
+
+	mrst->dev = NULL;
+	dev_set_drvdata(dev, NULL);
+}
+
+#ifdef	CONFIG_PM
+static int mrst_suspend(struct device *dev, pm_message_t mesg)
+{
+	struct mrst_rtc	*mrst = dev_get_drvdata(dev);
+	unsigned char	tmp;
+
+	/* Only the alarm might be a wakeup event source */
+	spin_lock_irq(&rtc_lock);
+	mrst->suspend_ctrl = tmp = vrtc_cmos_read(RTC_CONTROL);
+	if (tmp & (RTC_PIE | RTC_AIE)) {
+		unsigned char	mask;
+
+		if (device_may_wakeup(dev))
+			mask = RTC_IRQMASK & ~RTC_AIE;
+		else
+			mask = RTC_IRQMASK;
+		tmp &= ~mask;
+		vrtc_cmos_write(tmp, RTC_CONTROL);
+
+		mrst_checkintr(mrst, tmp);
+	}
+	spin_unlock_irq(&rtc_lock);
+
+	if (tmp & RTC_AIE) {
+		mrst->enabled_wake = 1;
+		enable_irq_wake(mrst->irq);
+	}
+
+	dev_dbg(&mrst_rtc.rtc->dev, "suspend%s, ctrl %02x\n",
+			(tmp & RTC_AIE) ? ", alarm may wake" : "",
+			tmp);
+
+	return 0;
+}
+
+/*
+ * We want RTC alarms to wake us from the deep power saving state
+ */
+static inline int mrst_poweroff(struct device *dev)
+{
+	return mrst_suspend(dev, PMSG_HIBERNATE);
+}
+
+static int mrst_resume(struct device *dev)
+{
+	struct mrst_rtc	*mrst = dev_get_drvdata(dev);
+	unsigned char tmp = mrst->suspend_ctrl;
+
+	/* Re-enable any irqs previously active */
+	if (tmp & RTC_IRQMASK) {
+		unsigned char	mask;
+
+		if (mrst->enabled_wake) {
+			disable_irq_wake(mrst->irq);
+			mrst->enabled_wake = 0;
+		}
+
+		spin_lock_irq(&rtc_lock);
+		do {
+			vrtc_cmos_write(tmp, RTC_CONTROL);
+
+			mask = vrtc_cmos_read(RTC_INTR_FLAGS);
+			mask &= (tmp & RTC_IRQMASK) | RTC_IRQF;
+			if (!is_intr(mask))
+				break;
+
+			rtc_update_irq(mrst->rtc, 1, mask);
+			tmp &= ~RTC_AIE;
+		} while (mask & RTC_AIE);
+		spin_unlock_irq(&rtc_lock);
+	}
+
+	dev_dbg(&mrst_rtc.rtc->dev, "resume, ctrl %02x\n", tmp);
+
+	return 0;
+}
+
+#else
+#define	mrst_suspend	NULL
+#define	mrst_resume	NULL
+
+static inline int mrst_poweroff(struct device *dev)
+{
+	return -ENOSYS;
+}
+
+#endif
+
+static int __init vrtc_mrst_platform_probe(struct platform_device *pdev)
+{
+	return vrtc_mrst_do_probe(&pdev->dev,
+			platform_get_resource(pdev, IORESOURCE_MEM, 0),
+			platform_get_irq(pdev, 0));
+}
+
+static int __exit vrtc_mrst_platform_remove(struct platform_device *pdev)
+{
+	rtc_mrst_do_remove(&pdev->dev);
+	return 0;
+}
+
+static void vrtc_mrst_platform_shutdown(struct platform_device *pdev)
+{
+	if (system_state == SYSTEM_POWER_OFF && !mrst_poweroff(&pdev->dev))
+		return;
+
+	rtc_mrst_do_shutdown();
+}
+
+MODULE_ALIAS("platform:vrtc_mrst");
+
+static struct platform_driver vrtc_mrst_platform_driver = {
+	.probe		= vrtc_mrst_platform_probe,
+	.remove		= __exit_p(vrtc_mrst_platform_remove),
+	.shutdown	= vrtc_mrst_platform_shutdown,
+	.driver = {
+		.name		= (char *) driver_name,
+		.suspend	= mrst_suspend,
+		.resume		= mrst_resume,
+	}
+};
+
+static int __init vrtc_mrst_init(void)
+{
+	return platform_driver_register(&vrtc_mrst_platform_driver);
+}
+
+static void __exit vrtc_mrst_exit(void)
+{
+	platform_driver_unregister(&vrtc_mrst_platform_driver);
+}
+
+module_init(vrtc_mrst_init);
+module_exit(vrtc_mrst_exit);
+
+MODULE_AUTHOR("Jacob Pan; Feng Tang");
+MODULE_DESCRIPTION("Driver for Moorestown virtual RTC");
+MODULE_LICENSE("GPL");

fs/gfs2/bmap.c

@@ -763,7 +763,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	int metadata;
 	unsigned int revokes = 0;
 	int x;
-	int error;
+	int error = 0;
 
 	if (!*top)
 		sm->sm_first = 0;
@@ -780,7 +780,11 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	if (metadata)
 		revokes = (height) ? sdp->sd_inptrs : sdp->sd_diptrs;
 
-	error = gfs2_rindex_hold(sdp, &ip->i_alloc->al_ri_gh);
+	if (ip != GFS2_I(sdp->sd_rindex))
+		error = gfs2_rindex_hold(sdp, &ip->i_alloc->al_ri_gh);
+	else if (!sdp->sd_rgrps)
+		error = gfs2_ri_update(ip);
+
 	if (error)
 		return error;
 
@@ -879,7 +883,8 @@ out_rg_gunlock:
 out_rlist:
 	gfs2_rlist_free(&rlist);
 out:
-	gfs2_glock_dq_uninit(&ip->i_alloc->al_ri_gh);
+	if (ip != GFS2_I(sdp->sd_rindex))
+		gfs2_glock_dq_uninit(&ip->i_alloc->al_ri_gh);
 	return error;
 }
 

fs/gfs2/glock.c

@@ -541,21 +541,6 @@ out_locked:
 	spin_unlock(&gl->gl_spin);
 }
 
-static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
-				 unsigned int req_state,
-				 unsigned int flags)
-{
-	int ret = LM_OUT_ERROR;
-
-	if (!sdp->sd_lockstruct.ls_ops->lm_lock)
-		return req_state == LM_ST_UNLOCKED ? 0 : req_state;
-
-	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
-		ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock,
-							 req_state, flags);
-	return ret;
-}
-
 /**
  * do_xmote - Calls the DLM to change the state of a lock
  * @gl: The lock state
@@ -575,13 +560,14 @@ __acquires(&gl->gl_spin)
 
 	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
 		      LM_FLAG_PRIORITY);
-	BUG_ON(gl->gl_state == target);
-	BUG_ON(gl->gl_state == gl->gl_target);
+	GLOCK_BUG_ON(gl, gl->gl_state == target);
+	GLOCK_BUG_ON(gl, gl->gl_state == gl->gl_target);
 	if ((target == LM_ST_UNLOCKED || target == LM_ST_DEFERRED) &&
 	    glops->go_inval) {
 		set_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
 		do_error(gl, 0); /* Fail queued try locks */
 	}
+	gl->gl_req = target;
 	spin_unlock(&gl->gl_spin);
 	if (glops->go_xmote_th)
 		glops->go_xmote_th(gl);
@@ -594,15 +580,17 @@ __acquires(&gl->gl_spin)
 	    gl->gl_state == LM_ST_DEFERRED) &&
 	    !(lck_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)))
 		lck_flags |= LM_FLAG_TRY_1CB;
-	ret = gfs2_lm_lock(sdp, gl, target, lck_flags);
 
-	if (!(ret & LM_OUT_ASYNC)) {
-		finish_xmote(gl, ret);
+	if (sdp->sd_lockstruct.ls_ops->lm_lock)	{
+		/* lock_dlm */
+		ret = sdp->sd_lockstruct.ls_ops->lm_lock(gl, target, lck_flags);
+		GLOCK_BUG_ON(gl, ret);
+	} else { /* lock_nolock */
+		finish_xmote(gl, target);
 		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
 			gfs2_glock_put(gl);
-	} else {
-		GLOCK_BUG_ON(gl, ret != LM_OUT_ASYNC);
 	}
+
 	spin_lock(&gl->gl_spin);
 }
 
@@ -951,17 +939,22 @@ int gfs2_glock_wait(struct gfs2_holder *gh)
 
 void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
+
 	if (seq) {
 		struct gfs2_glock_iter *gi = seq->private;
 		vsprintf(gi->string, fmt, args);
 		seq_printf(seq, gi->string);
 	} else {
-		printk(KERN_ERR " ");
-		vprintk(fmt, args);
+		vaf.fmt = fmt;
+		vaf.va = &args;
+
+		printk(KERN_ERR " %pV", &vaf);
 	}
+
 	va_end(args);
 }
 
@@ -1361,24 +1354,28 @@ static int gfs2_should_freeze(const struct gfs2_glock *gl)
  * @gl: Pointer to the glock
  * @ret: The return value from the dlm
  *
+ * The gl_reply field is under the gl_spin lock so that it is ok
+ * to use a bitfield shared with other glock state fields.
  */
 
 void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
 {
 	struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
 
+	spin_lock(&gl->gl_spin);
 	gl->gl_reply = ret;
 
 	if (unlikely(test_bit(DFL_BLOCK_LOCKS, &ls->ls_flags))) {
-		spin_lock(&gl->gl_spin);
 		if (gfs2_should_freeze(gl)) {
 			set_bit(GLF_FROZEN, &gl->gl_flags);
 			spin_unlock(&gl->gl_spin);
 			return;
 		}
-		spin_unlock(&gl->gl_spin);
 	}
+
+	spin_unlock(&gl->gl_spin);
 	set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
+	smp_wmb();
 	gfs2_glock_hold(gl);
 	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
 		gfs2_glock_put(gl);
@@ -1626,18 +1623,17 @@ static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
 static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh)
 {
 	struct task_struct *gh_owner = NULL;
-	char buffer[KSYM_SYMBOL_LEN];
 	char flags_buf[32];
 
-	sprint_symbol(buffer, gh->gh_ip);
 	if (gh->gh_owner_pid)
 		gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID);
-	gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %s\n",
-		  state2str(gh->gh_state),
-		  hflags2str(flags_buf, gh->gh_flags, gh->gh_iflags),
-		  gh->gh_error, 
-		  gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1,
-		  gh_owner ? gh_owner->comm : "(ended)", buffer);
+	gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %pS\n",
+		       state2str(gh->gh_state),
+		       hflags2str(flags_buf, gh->gh_flags, gh->gh_iflags),
+		       gh->gh_error,
+		       gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1,
+		       gh_owner ? gh_owner->comm : "(ended)",
+		       (void *)gh->gh_ip);
 	return 0;
 }
 
@@ -1782,12 +1778,13 @@ int __init gfs2_glock_init(void)
 	}
 #endif
 
-	glock_workqueue = alloc_workqueue("glock_workqueue", WQ_RESCUER |
+	glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM |
 					  WQ_HIGHPRI | WQ_FREEZEABLE, 0);
 	if (IS_ERR(glock_workqueue))
 		return PTR_ERR(glock_workqueue);
-	gfs2_delete_workqueue = alloc_workqueue("delete_workqueue", WQ_RESCUER |
-						WQ_FREEZEABLE, 0);
+	gfs2_delete_workqueue = alloc_workqueue("delete_workqueue",
+						WQ_MEM_RECLAIM | WQ_FREEZEABLE,
+						0);
 	if (IS_ERR(gfs2_delete_workqueue)) {
 		destroy_workqueue(glock_workqueue);
 		return PTR_ERR(gfs2_delete_workqueue);

fs/gfs2/glock.h

@@ -87,11 +87,10 @@ enum {
 #define GL_ASYNC		0x00000040
 #define GL_EXACT		0x00000080
 #define GL_SKIP			0x00000100
-#define GL_ATIME		0x00000200
 #define GL_NOCACHE		0x00000400
   
 /*
- * lm_lock() and lm_async_cb return flags
+ * lm_async_cb return flags
  *
  * LM_OUT_ST_MASK
  * Masks the lower two bits of lock state in the returned value.
@@ -99,15 +98,11 @@ enum {
  * LM_OUT_CANCELED
  * The lock request was canceled.
  *
- * LM_OUT_ASYNC
- * The result of the request will be returned in an LM_CB_ASYNC callback.
- *
  */
 
 #define LM_OUT_ST_MASK		0x00000003
 #define LM_OUT_CANCELED		0x00000008
-#define LM_OUT_ASYNC		0x00000080
-#define LM_OUT_ERROR		0x00000100
+#define LM_OUT_ERROR		0x00000004
 
 /*
  * lm_recovery_done() messages
@@ -124,25 +119,12 @@ struct lm_lockops {
  	void (*lm_unmount) (struct gfs2_sbd *sdp);
 	void (*lm_withdraw) (struct gfs2_sbd *sdp);
 	void (*lm_put_lock) (struct kmem_cache *cachep, struct gfs2_glock *gl);
-	unsigned int (*lm_lock) (struct gfs2_glock *gl,
-				 unsigned int req_state, unsigned int flags);
+	int (*lm_lock) (struct gfs2_glock *gl, unsigned int req_state,
+			unsigned int flags);
 	void (*lm_cancel) (struct gfs2_glock *gl);
 	const match_table_t *lm_tokens;
 };
 
-#define LM_FLAG_TRY		0x00000001
-#define LM_FLAG_TRY_1CB		0x00000002
-#define LM_FLAG_NOEXP		0x00000004
-#define LM_FLAG_ANY		0x00000008
-#define LM_FLAG_PRIORITY	0x00000010
-
-#define GL_ASYNC		0x00000040
-#define GL_EXACT		0x00000080
-#define GL_SKIP			0x00000100
-#define GL_NOCACHE		0x00000400
-
-#define GLR_TRYFAILED		13
-
 extern struct workqueue_struct *gfs2_delete_workqueue;
 static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
 {
@@ -212,6 +194,8 @@ int gfs2_glock_nq_num(struct gfs2_sbd *sdp,
 int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
 void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
 void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs);
+
+__attribute__ ((format(printf, 2, 3)))
 void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...);
 
 /**

fs/gfs2/glops.c

@@ -325,7 +325,6 @@ static void trans_go_sync(struct gfs2_glock *gl)
 
 	if (gl->gl_state != LM_ST_UNLOCKED &&
 	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
-		flush_workqueue(gfs2_delete_workqueue);
 		gfs2_meta_syncfs(sdp);
 		gfs2_log_shutdown(sdp);
 	}

fs/gfs2/incore.h

@@ -207,12 +207,14 @@ struct gfs2_glock {
 
 	spinlock_t gl_spin;
 
-	unsigned int gl_state;
-	unsigned int gl_target;
-	unsigned int gl_reply;
+	/* State fields protected by gl_spin */
+	unsigned int gl_state:2,	/* Current state */
+		     gl_target:2,	/* Target state */
+		     gl_demote_state:2,	/* State requested by remote node */
+		     gl_req:2,		/* State in last dlm request */
+		     gl_reply:8;	/* Last reply from the dlm */
+
 	unsigned int gl_hash;
-	unsigned int gl_req;
-	unsigned int gl_demote_state; /* state requested by remote node */
 	unsigned long gl_demote_time; /* time of first demote request */
 	struct list_head gl_holders;
 

fs/gfs2/inode.c

@@ -916,17 +916,8 @@ static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
 	if (error)
 		return error;
 
-	if ((attr->ia_valid & ATTR_SIZE) &&
-	    attr->ia_size != i_size_read(inode)) {
-		error = vmtruncate(inode, attr->ia_size);
-		if (error)
-			return error;
-	}
-
 	setattr_copy(inode, attr);
 	mark_inode_dirty(inode);
-
-	gfs2_assert_warn(GFS2_SB(inode), !error);
 	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
 	gfs2_dinode_out(ip, dibh->b_data);
 	brelse(dibh);

fs/gfs2/lock_dlm.c

@@ -146,15 +146,13 @@ static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
 	return lkf;
 }
 
-static unsigned int gdlm_lock(struct gfs2_glock *gl,
-			      unsigned int req_state, unsigned int flags)
+static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
+		     unsigned int flags)
 {
 	struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
-	int error;
 	int req;
 	u32 lkf;
 
-	gl->gl_req = req_state;
 	req = make_mode(req_state);
 	lkf = make_flags(gl->gl_lksb.sb_lkid, flags, req);
 
@@ -162,13 +160,8 @@ static unsigned int gdlm_lock(struct gfs2_glock *gl,
 	 * Submit the actual lock request.
 	 */
 
-	error = dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, gl->gl_strname,
-			 GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast);
-	if (error == -EAGAIN)
-		return 0;
-	if (error)
-		return LM_OUT_ERROR;
-	return LM_OUT_ASYNC;
+	return dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, gl->gl_strname,
+			GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast);
 }
 
 static void gdlm_put_lock(struct kmem_cache *cachep, struct gfs2_glock *gl)

fs/gfs2/ops_inode.c

@@ -1069,7 +1069,6 @@ static int setattr_chown(struct inode *inode, struct iattr *attr)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct buffer_head *dibh;
 	u32 ouid, ogid, nuid, ngid;
 	int error;
 
@@ -1100,25 +1099,10 @@ static int setattr_chown(struct inode *inode, struct iattr *attr)
 	if (error)
 		goto out_gunlock_q;
 
-	error = gfs2_meta_inode_buffer(ip, &dibh);
+	error = gfs2_setattr_simple(ip, attr);
 	if (error)
 		goto out_end_trans;
 
-	if ((attr->ia_valid & ATTR_SIZE) &&
-	    attr->ia_size != i_size_read(inode)) {
-		int error;
-
-		error = vmtruncate(inode, attr->ia_size);
-		gfs2_assert_warn(sdp, !error);
-	}
-
-	setattr_copy(inode, attr);
-	mark_inode_dirty(inode);
-
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-	gfs2_dinode_out(ip, dibh->b_data);
-	brelse(dibh);
-
 	if (ouid != NO_QUOTA_CHANGE || ogid != NO_QUOTA_CHANGE) {
 		u64 blocks = gfs2_get_inode_blocks(&ip->i_inode);
 		gfs2_quota_change(ip, -blocks, ouid, ogid);

fs/gfs2/quota.c

@@ -666,6 +666,10 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 			qp->qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift);
 			qd->qd_qb.qb_limit = qp->qu_limit;
 		}
+		if (fdq->d_fieldmask & FS_DQ_BCOUNT) {
+			qp->qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift);
+			qd->qd_qb.qb_value = qp->qu_value;
+		}
 	}
 
 	/* Write the quota into the quota file on disk */
@@ -1509,7 +1513,7 @@ out:
 }
 
 /* GFS2 only supports a subset of the XFS fields */
-#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD)
+#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD|FS_DQ_BCOUNT)
 
 static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id,
 			  struct fs_disk_quota *fdq)
@@ -1569,9 +1573,15 @@ static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id,
 	if ((fdq->d_fieldmask & FS_DQ_BSOFT) &&
 	    ((fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_warn)))
 		fdq->d_fieldmask ^= FS_DQ_BSOFT;
+
 	if ((fdq->d_fieldmask & FS_DQ_BHARD) &&
 	    ((fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_limit)))
 		fdq->d_fieldmask ^= FS_DQ_BHARD;
+
+	if ((fdq->d_fieldmask & FS_DQ_BCOUNT) &&
+	    ((fdq->d_bcount >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_value)))
+		fdq->d_fieldmask ^= FS_DQ_BCOUNT;
+
 	if (fdq->d_fieldmask == 0)
 		goto out_i;
 
@@ -1620,4 +1630,3 @@ const struct quotactl_ops gfs2_quotactl_ops = {
 	.get_dqblk	= gfs2_get_dqblk,
 	.set_dqblk	= gfs2_set_dqblk,
 };
-

fs/gfs2/rgrp.c

@@ -500,7 +500,7 @@ u64 gfs2_ri_total(struct gfs2_sbd *sdp)
 	for (rgrps = 0;; rgrps++) {
 		loff_t pos = rgrps * sizeof(struct gfs2_rindex);
 
-		if (pos + sizeof(struct gfs2_rindex) >= i_size_read(inode))
+		if (pos + sizeof(struct gfs2_rindex) > i_size_read(inode))
 			break;
 		error = gfs2_internal_read(ip, &ra_state, buf, &pos,
 					   sizeof(struct gfs2_rindex));
@@ -583,7 +583,7 @@ static int read_rindex_entry(struct gfs2_inode *ip,
  * Returns: 0 on successful update, error code otherwise
  */
 
-static int gfs2_ri_update(struct gfs2_inode *ip)
+int gfs2_ri_update(struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct inode *inode = &ip->i_inode;
@@ -613,46 +613,6 @@ static int gfs2_ri_update(struct gfs2_inode *ip)
 	return 0;
 }
 
-/**
- * gfs2_ri_update_special - Pull in a new resource index from the disk
- *
- * This is a special version that's safe to call from gfs2_inplace_reserve_i.
- * In this case we know that we don't have any resource groups in memory yet.
- *
- * @ip: pointer to the rindex inode
- *
- * Returns: 0 on successful update, error code otherwise
- */
-static int gfs2_ri_update_special(struct gfs2_inode *ip)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct inode *inode = &ip->i_inode;
-	struct file_ra_state ra_state;
-	struct gfs2_rgrpd *rgd;
-	unsigned int max_data = 0;
-	int error;
-
-	file_ra_state_init(&ra_state, inode->i_mapping);
-	for (sdp->sd_rgrps = 0;; sdp->sd_rgrps++) {
-		/* Ignore partials */
-		if ((sdp->sd_rgrps + 1) * sizeof(struct gfs2_rindex) >
-		    i_size_read(inode))
-			break;
-		error = read_rindex_entry(ip, &ra_state);
-		if (error) {
-			clear_rgrpdi(sdp);
-			return error;
-		}
-	}
-	list_for_each_entry(rgd, &sdp->sd_rindex_list, rd_list)
-		if (rgd->rd_data > max_data)
-			max_data = rgd->rd_data;
-	sdp->sd_max_rg_data = max_data;
-
-	sdp->sd_rindex_uptodate = 1;
-	return 0;
-}
-
 /**
  * gfs2_rindex_hold - Grab a lock on the rindex
  * @sdp: The GFS2 superblock
@@ -1226,16 +1186,25 @@ int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
 			error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
 		else if (!sdp->sd_rgrps) /* We may not have the rindex read
 					    in, so: */
-			error = gfs2_ri_update_special(ip);
+			error = gfs2_ri_update(ip);
 		if (error)
 			return error;
 	}
 
+try_again:
 	do {
 		error = get_local_rgrp(ip, &last_unlinked);
 		/* If there is no space, flushing the log may release some */
-		if (error)
+		if (error) {
+			if (ip == GFS2_I(sdp->sd_rindex) &&
+			    !sdp->sd_rindex_uptodate) {
+				error = gfs2_ri_update(ip);
+				if (error)
+					return error;
+				goto try_again;
+			}
 			gfs2_log_flush(sdp, NULL);
+		}
 	} while (error && tries++ < 3);
 
 	if (error) {

fs/gfs2/rgrp.h

@@ -48,6 +48,7 @@ extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
 
 extern void gfs2_inplace_release(struct gfs2_inode *ip);
 
+extern int gfs2_ri_update(struct gfs2_inode *ip);
 extern int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n);
 extern int gfs2_alloc_di(struct gfs2_inode *ip, u64 *bn, u64 *generation);