Merge ssh://master.kernel.org/pub/scm/linux/kernel/git/tglx/linux-2.6-x86

* ssh://master.kernel.org/pub/scm/linux/kernel/git/tglx/linux-2.6-x86: (114 commits)
  x86: delete vsyscall files during make clean
  kbuild: fix typo SRCARCH in find_sources
  x86: fix kernel rebuild due to vsyscall fallout
  .gitignore update for x86 arch
  x86: unify include/asm/debugreg_32/64.h
  x86: unify include/asm/unwind_32/64.h
  x86: unify include/asm/types_32/64.h
  x86: unify include/asm/tlb_32/64.h
  x86: unify include/asm/siginfo_32/64.h
  x86: unify include/asm/bug_32/64.h
  x86: unify include/asm/mman_32/64.h
  x86: unify include/asm/agp_32/64.h
  x86: unify include/asm/kdebug_32/64.h
  x86: unify include/asm/ioctls_32/64.h
  x86: unify include/asm/floppy_32/64.h
  x86: apply missing DMA/OOM prevention to floppy_32.h
  x86: unify include/asm/cache_32/64.h
  x86: unify include/asm/cache_32/64.h
  x86: unify include/asm/dmi_32/64.h
  x86: unify include/asm/delay_32/64.h
  ...

.gitignore

@@ -26,6 +26,7 @@ vmlinux*
 !vmlinux.lds.S
 System.map
 Module.symvers
+!.gitignore
 
 #
 # Generated include files

Documentation/filesystems/proc.txt

@@ -347,7 +347,35 @@ connects the CPUs in a SMP system. This means that an error has been detected,
 the IO-APIC automatically retry the transmission, so it should not be a big
 problem, but you should read the SMP-FAQ.
 
-In this context it could be interesting to note the new irq directory in 2.4.
+In 2.6.2* /proc/interrupts was expanded again.  This time the goal was for
+/proc/interrupts to display every IRQ vector in use by the system, not
+just those considered 'most important'.  The new vectors are:
+
+  THR -- interrupt raised when a machine check threshold counter
+  (typically counting ECC corrected errors of memory or cache) exceeds
+  a configurable threshold.  Only available on some systems.
+
+  TRM -- a thermal event interrupt occurs when a temperature threshold
+  has been exceeded for the CPU.  This interrupt may also be generated
+  when the temperature drops back to normal.
+
+  SPU -- a spurious interrupt is some interrupt that was raised then lowered
+  by some IO device before it could be fully processed by the APIC.  Hence
+  the APIC sees the interrupt but does not know what device it came from.
+  For this case the APIC will generate the interrupt with a IRQ vector
+  of 0xff. This might also be generated by chipset bugs.
+
+  RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
+  sent from one CPU to another per the needs of the OS.  Typically,
+  their statistics are used by kernel developers and interested users to
+  determine the occurance of interrupt of the given type.
+
+The above IRQ vectors are displayed only when relevent.  For example,
+the threshold vector does not exist on x86_64 platforms.  Others are
+suppressed when the system is a uniprocessor.  As of this writing, only
+i386 and x86_64 platforms support the new IRQ vector displays.
+
+Of some interest is the introduction of the /proc/irq directory to 2.4.
 It could be used to set IRQ to CPU affinity, this means that you can "hook" an
 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
 irq subdir is one subdir for each IRQ, and one file; prof_cpu_mask

Documentation/kernel-parameters.txt

@@ -994,6 +994,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	mce		[X86-32] Machine Check Exception
 
+	mce=option	[X86-64] See Documentation/x86_64/boot-options.txt
+
 	md=		[HW] RAID subsystems devices and level
 			See Documentation/md.txt.
 

Makefile

@@ -1325,8 +1325,8 @@ ALLSOURCE_ARCHS := $(ARCH) $(SRCARCH)
 endif
 
 define find-sources
-        ( for ARCH in $(ALLSOURCE_ARCHS) ; do \
-	       find $(__srctree)arch/$${SRCARCH} $(RCS_FIND_IGNORE) \
+        ( for arch in $(ALLSOURCE_ARCHS) ; do \
+	       find $(__srctree)arch/$${arch} $(RCS_FIND_IGNORE) \
 	            -name $1 -print; \
 	  done ; \
 	  find $(__srctree)security/selinux/include $(RCS_FIND_IGNORE) \
@@ -1334,8 +1334,8 @@ define find-sources
 	  find $(__srctree)include $(RCS_FIND_IGNORE) \
 	       \( -name config -o -name 'asm-*' \) -prune \
 	       -o -name $1 -print; \
-	  for ARCH in $(ALLINCLUDE_ARCHS) ; do \
-	       find $(__srctree)include/asm-$${SRCARCH} $(RCS_FIND_IGNORE) \
+	  for arch in $(ALLINCLUDE_ARCHS) ; do \
+	       find $(__srctree)include/asm-$${arch} $(RCS_FIND_IGNORE) \
 	            -name $1 -print; \
 	  done ; \
 	  find $(__srctree)include/asm-generic $(RCS_FIND_IGNORE) \

arch/i386/.gitignore

+boot

arch/i386/Kconfig

@@ -146,6 +146,7 @@ config X86_ELAN
 
 config X86_VOYAGER
 	bool "Voyager (NCR)"
+	select SMP if !BROKEN
 	help
 	  Voyager is an MCA-based 32-way capable SMP architecture proprietary
 	  to NCR Corp.  Machine classes 345x/35xx/4100/51xx are Voyager-based.

arch/i386/Kconfig.cpu

@@ -109,16 +109,42 @@ config MCORE2
 	help
 	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and 53xx)
 	  CPUs. You can distinguish newer from older Xeons by the CPU family
-	  in /proc/cpuinfo. Newer ones have 6.
+	  in /proc/cpuinfo. Newer ones have 6 and older ones 15 (not a typo)
 
 config MPENTIUM4
 	bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon"
 	help
 	  Select this for Intel Pentium 4 chips.  This includes the
-	  Pentium 4, P4-based Celeron and Xeon, and Pentium-4 M
-	  (not Pentium M) chips.  This option enables compile flags
-	  optimized for the chip, uses the correct cache shift, and
-	  applies any applicable Pentium III optimizations.
+	  Pentium 4, Pentium D, P4-based Celeron and Xeon, and
+	  Pentium-4 M (not Pentium M) chips.  This option enables compile
+	  flags optimized for the chip, uses the correct cache line size, and
+	  applies any applicable optimizations.
+
+	  CPUIDs: F[0-6][1-A] (in /proc/cpuinfo show = cpu family : 15 )
+
+	  Select this for:
+	    Pentiums (Pentium 4, Pentium D, Celeron, Celeron D) corename:
+		-Willamette
+		-Northwood
+		-Mobile Pentium 4
+		-Mobile Pentium 4 M
+		-Extreme Edition (Gallatin)
+		-Prescott
+		-Prescott 2M
+		-Cedar Mill
+		-Presler
+		-Smithfiled
+	    Xeons (Intel Xeon, Xeon MP, Xeon LV, Xeon MV) corename:
+		-Foster
+		-Prestonia
+		-Gallatin
+		-Nocona
+		-Irwindale
+		-Cranford
+		-Potomac
+		-Paxville
+		-Dempsey
+
 
 config MK6
 	bool "K6/K6-II/K6-III"

arch/x86/ia32/Makefile

@@ -18,18 +18,35 @@ $(obj)/syscall32_syscall.o: \
 	$(foreach F,sysenter syscall,$(obj)/vsyscall-$F.so)
 
 # Teach kbuild about targets
-targets := $(foreach F,sysenter syscall,vsyscall-$F.o vsyscall-$F.so)
+targets := $(foreach F,$(addprefix vsyscall-,sysenter syscall),\
+		     $F.o $F.so $F.so.dbg)
 
 # The DSO images are built using a special linker script
 quiet_cmd_syscall = SYSCALL $@
-      cmd_syscall = $(CC) -m32 -nostdlib -shared -s \
+      cmd_syscall = $(CC) -m32 -nostdlib -shared \
 			  $(call ld-option, -Wl$(comma)--hash-style=sysv) \
 			   -Wl,-soname=linux-gate.so.1 -o $@ \
 			   -Wl,-T,$(filter-out FORCE,$^)
 
-$(obj)/vsyscall-sysenter.so $(obj)/vsyscall-syscall.so: \
-$(obj)/vsyscall-%.so: $(src)/vsyscall.lds $(obj)/vsyscall-%.o FORCE
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/vsyscall-sysenter.so.dbg $(obj)/vsyscall-syscall.so.dbg: \
+$(obj)/vsyscall-%.so.dbg: $(src)/vsyscall.lds $(obj)/vsyscall-%.o FORCE
 	$(call if_changed,syscall)
 
 AFLAGS_vsyscall-sysenter.o = -m32 -Wa,-32
 AFLAGS_vsyscall-syscall.o = -m32 -Wa,-32
+
+vdsos := vdso32-sysenter.so vdso32-syscall.so
+
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(@:vdso32-%.so=$(obj)/vsyscall-%.so.dbg) \
+			    $(MODLIB)/vdso/$@
+
+$(vdsos):
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+vdso_install: $(vdsos)

arch/x86/ia32/ia32_aout.c

@@ -420,6 +420,8 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 	(regs)->eflags = 0x200;
 	(regs)->cs = __USER32_CS;
 	(regs)->ss = __USER32_DS;
+	regs->r8 = regs->r9 = regs->r10 = regs->r11 =
+	regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
 	set_fs(USER_DS);
 	if (unlikely(current->ptrace & PT_PTRACED)) {
 		if (current->ptrace & PT_TRACE_EXEC)

arch/x86/ia32/ia32_binfmt.c

@@ -112,11 +112,8 @@ struct elf_prpsinfo
 	char	pr_psargs[ELF_PRARGSZ];	/* initial part of arg list */
 };
 
-#define __STR(x) #x
-#define STR(x) __STR(x)
-
 #define _GET_SEG(x) \
-	({ __u32 seg; asm("movl %%" STR(x) ",%0" : "=r"(seg)); seg; })
+	({ __u32 seg; asm("movl %%" __stringify(x) ",%0" : "=r"(seg)); seg; })
 
 /* Assumes current==process to be dumped */
 #define ELF_CORE_COPY_REGS(pr_reg, regs)       		\

arch/x86/ia32/ptrace32.c

@@ -228,6 +228,8 @@ static long ptrace32_siginfo(unsigned request, u32 pid, u32 addr, u32 data)
 	return ret;
 }
 
+#define COMPAT_GDT_ENTRY_TLS_MIN 6
+
 asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 {
 	struct task_struct *child;
@@ -246,8 +248,6 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 	case PTRACE_SYSCALL:
 	case PTRACE_OLDSETOPTIONS:
 	case PTRACE_SETOPTIONS:
-	case PTRACE_SET_THREAD_AREA:
-	case PTRACE_GET_THREAD_AREA:
 		return sys_ptrace(request, pid, addr, data); 
 
 	default:
@@ -271,6 +271,12 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 	case PTRACE_SETSIGINFO:
 	case PTRACE_GETSIGINFO:
 		return ptrace32_siginfo(request, pid, addr, data);
+
+	case PTRACE_SET_THREAD_AREA:
+	case PTRACE_GET_THREAD_AREA:
+		return sys_ptrace(request, pid,
+			addr + GDT_ENTRY_TLS_MIN - COMPAT_GDT_ENTRY_TLS_MIN,
+			data);
 	}
 
 	child = ptrace_get_task_struct(pid);

arch/x86/kernel/.gitignore

 vsyscall.lds
+vsyscall_32.lds

arch/x86/kernel/Makefile

@@ -3,3 +3,7 @@ include ${srctree}/arch/x86/kernel/Makefile_32
 else
 include ${srctree}/arch/x86/kernel/Makefile_64
 endif
+
+# Workaround to delete .lds files with make clean
+# The problem is that we do not enter Makefile_32 with make clean.
+clean-files := vsyscall*.lds vsyscall*.so

arch/x86/kernel/Makefile_32

@@ -51,7 +51,7 @@ obj-$(CONFIG_SCx200)		+= scx200_32.o
 # We must build both images before we can assemble it.
 # Note: kbuild does not track this dependency due to usage of .incbin
 $(obj)/vsyscall_32.o: $(obj)/vsyscall-int80_32.so $(obj)/vsyscall-sysenter_32.so
-targets += $(foreach F,int80 sysenter,vsyscall-$F.o vsyscall-$F.so)
+targets += $(foreach F,int80 sysenter,vsyscall-$F_32.o vsyscall-$F_32.so)
 targets += vsyscall-note_32.o vsyscall_32.lds
 
 # The DSO images are built using a special linker script.

arch/x86/kernel/alternative.c

@@ -63,11 +63,11 @@ __setup("noreplace-paravirt", setup_noreplace_paravirt);
 /* Use inline assembly to define this because the nops are defined
    as inline assembly strings in the include files and we cannot
    get them easily into strings. */
-asm("\t.data\nintelnops: "
+asm("\t.section .rodata, \"a\"\nintelnops: "
 	GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
 	GENERIC_NOP7 GENERIC_NOP8);
-extern unsigned char intelnops[];
-static unsigned char *intel_nops[ASM_NOP_MAX+1] = {
+extern const unsigned char intelnops[];
+static const unsigned char *const intel_nops[ASM_NOP_MAX+1] = {
 	NULL,
 	intelnops,
 	intelnops + 1,
@@ -81,11 +81,11 @@ static unsigned char *intel_nops[ASM_NOP_MAX+1] = {
 #endif
 
 #ifdef K8_NOP1
-asm("\t.data\nk8nops: "
+asm("\t.section .rodata, \"a\"\nk8nops: "
 	K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
 	K8_NOP7 K8_NOP8);
-extern unsigned char k8nops[];
-static unsigned char *k8_nops[ASM_NOP_MAX+1] = {
+extern const unsigned char k8nops[];
+static const unsigned char *const k8_nops[ASM_NOP_MAX+1] = {
 	NULL,
 	k8nops,
 	k8nops + 1,
@@ -99,11 +99,11 @@ static unsigned char *k8_nops[ASM_NOP_MAX+1] = {
 #endif
 
 #ifdef K7_NOP1
-asm("\t.data\nk7nops: "
+asm("\t.section .rodata, \"a\"\nk7nops: "
 	K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
 	K7_NOP7 K7_NOP8);
-extern unsigned char k7nops[];
-static unsigned char *k7_nops[ASM_NOP_MAX+1] = {
+extern const unsigned char k7nops[];
+static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = {
 	NULL,
 	k7nops,
 	k7nops + 1,
@@ -116,28 +116,49 @@ static unsigned char *k7_nops[ASM_NOP_MAX+1] = {
 };
 #endif
 
+#ifdef P6_NOP1
+asm("\t.section .rodata, \"a\"\np6nops: "
+	P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6
+	P6_NOP7 P6_NOP8);
+extern const unsigned char p6nops[];
+static const unsigned char *const p6_nops[ASM_NOP_MAX+1] = {
+	NULL,
+	p6nops,
+	p6nops + 1,
+	p6nops + 1 + 2,
+	p6nops + 1 + 2 + 3,
+	p6nops + 1 + 2 + 3 + 4,
+	p6nops + 1 + 2 + 3 + 4 + 5,
+	p6nops + 1 + 2 + 3 + 4 + 5 + 6,
+	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+#endif
+
 #ifdef CONFIG_X86_64
 
 extern char __vsyscall_0;
-static inline unsigned char** find_nop_table(void)
+static inline const unsigned char*const * find_nop_table(void)
 {
-	return k8_nops;
+	return boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
+	       boot_cpu_data.x86 < 6 ? k8_nops : p6_nops;
 }
 
 #else /* CONFIG_X86_64 */
 
-static struct nop {
+static const struct nop {
 	int cpuid;
-	unsigned char **noptable;
+	const unsigned char *const *noptable;
 } noptypes[] = {
 	{ X86_FEATURE_K8, k8_nops },
 	{ X86_FEATURE_K7, k7_nops },
+	{ X86_FEATURE_P4, p6_nops },
+	{ X86_FEATURE_P3, p6_nops },
 	{ -1, NULL }
 };
 
-static unsigned char** find_nop_table(void)
+static const unsigned char*const * find_nop_table(void)
 {
-	unsigned char **noptable = intel_nops;
+	const unsigned char *const *noptable = intel_nops;
 	int i;
 
 	for (i = 0; noptypes[i].cpuid >= 0; i++) {
@@ -154,7 +175,7 @@ static unsigned char** find_nop_table(void)
 /* Use this to add nops to a buffer, then text_poke the whole buffer. */
 static void add_nops(void *insns, unsigned int len)
 {
-	unsigned char **noptable = find_nop_table();
+	const unsigned char *const *noptable = find_nop_table();
 
 	while (len > 0) {
 		unsigned int noplen = len;
@@ -415,9 +436,6 @@ void __init alternative_instructions(void)
 			alternatives_smp_unlock(__smp_locks, __smp_locks_end,
 						_text, _etext);
 		}
-		free_init_pages("SMP alternatives",
-				(unsigned long)__smp_locks,
-				(unsigned long)__smp_locks_end);
 	} else {
 		alternatives_smp_module_add(NULL, "core kernel",
 					    __smp_locks, __smp_locks_end,
@@ -428,6 +446,11 @@ void __init alternative_instructions(void)
  	apply_paravirt(__parainstructions, __parainstructions_end);
 	local_irq_restore(flags);
 
+	if (smp_alt_once)
+		free_init_pages("SMP alternatives",
+				(unsigned long)__smp_locks,
+				(unsigned long)__smp_locks_end);
+
 	restart_nmi();
 #ifdef CONFIG_X86_MCE
 	restart_mce();

arch/x86/kernel/apic_32.c

@@ -1277,6 +1277,7 @@ void smp_spurious_interrupt(struct pt_regs *regs)
 	/* see sw-dev-man vol 3, chapter 7.4.13.5 */
 	printk(KERN_INFO "spurious APIC interrupt on CPU#%d, "
 	       "should never happen.\n", smp_processor_id());
+	__get_cpu_var(irq_stat).irq_spurious_count++;
 	irq_exit();
 }
 

arch/x86/kernel/apic_64.c

@@ -974,15 +974,12 @@ void __init setup_boot_APIC_clock (void)
  */
 void __cpuinit check_boot_apic_timer_broadcast(void)
 {
-	struct clock_event_device *levt = &per_cpu(lapic_events, boot_cpu_id);
-
 	if (!disable_apic_timer ||
 	    (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY))
 		return;
 
 	printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n");
 	lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY;
-	levt->features |= CLOCK_EVT_FEAT_DUMMY;
 
 	local_irq_enable();
 	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, &boot_cpu_id);
@@ -1143,6 +1140,7 @@ asmlinkage void smp_spurious_interrupt(void)
 	if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
 		ack_APIC_irq();
 
+	add_pda(irq_spurious_count, 1);
 	irq_exit();
 }
 

arch/x86/kernel/cpu/amd.c

@@ -4,6 +4,7 @@
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
+#include <asm/mach_apic.h>
 
 #include "cpu.h"
 
@@ -45,13 +46,17 @@ static __cpuinit int amd_apic_timer_broken(void)
 	case CPUID_XFAM_10H:
 	case CPUID_XFAM_11H:
 		rdmsr(MSR_K8_ENABLE_C1E, lo, hi);
-		if (lo & ENABLE_C1E_MASK)
+		if (lo & ENABLE_C1E_MASK) {
+			if (smp_processor_id() != boot_cpu_physical_apicid)
+				printk(KERN_INFO "AMD C1E detected late. "
+				       "	Force timer broadcast.\n");
 			return 1;
-                break;
-        default:
-                /* err on the side of caution */
+		}
+		break;
+	default:
+		/* err on the side of caution */
 		return 1;
-        }
+	}
 	return 0;
 }
 #endif

arch/x86/kernel/cpu/cpufreq/powernow-k7.c

@@ -565,7 +565,7 @@ static unsigned int powernow_get(unsigned int cpu)
 }
 
 
-static int __init acer_cpufreq_pst(struct dmi_system_id *d)
+static int __init acer_cpufreq_pst(const struct dmi_system_id *d)
 {
 	printk(KERN_WARNING "%s laptop with broken PST tables in BIOS detected.\n", d->ident);
 	printk(KERN_WARNING "You need to downgrade to 3A21 (09/09/2002), or try a newer BIOS than 3A71 (01/20/2003)\n");

arch/x86/kernel/cpu/intel.c

@@ -8,6 +8,7 @@
 #include <linux/module.h>
 
 #include <asm/processor.h>
+#include <asm/pgtable.h>
 #include <asm/msr.h>
 #include <asm/uaccess.h>
 
@@ -19,8 +20,6 @@
 #include <mach_apic.h>
 #endif
 
-extern int trap_init_f00f_bug(void);
-
 #ifdef CONFIG_X86_INTEL_USERCOPY
 /*
  * Alignment at which movsl is preferred for bulk memory copies.
@@ -95,6 +94,20 @@ static int __cpuinit num_cpu_cores(struct cpuinfo_x86 *c)
 		return 1;
 }
 
+#ifdef CONFIG_X86_F00F_BUG
+static void __cpuinit trap_init_f00f_bug(void)
+{
+	__set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO);
+
+	/*
+	 * Update the IDT descriptor and reload the IDT so that
+	 * it uses the read-only mapped virtual address.
+	 */
+	idt_descr.address = fix_to_virt(FIX_F00F_IDT);
+	load_idt(&idt_descr);
+}
+#endif
+
 static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 {
 	unsigned int l2 = 0;

arch/x86/kernel/cpu/intel_cacheinfo.c

@@ -170,15 +170,15 @@ union l3_cache {
 	unsigned val;
 };
 
-static const unsigned short assocs[] = {
+static unsigned short assocs[] __cpuinitdata = {
 	[1] = 1, [2] = 2, [4] = 4, [6] = 8,
 	[8] = 16, [0xa] = 32, [0xb] = 48,
 	[0xc] = 64,
 	[0xf] = 0xffff // ??
 };
 
-static const unsigned char levels[] = { 1, 1, 2, 3 };
-static const unsigned char types[] = { 1, 2, 3, 3 };
+static unsigned char levels[] __cpuinitdata = { 1, 1, 2, 3 };
+static unsigned char types[] __cpuinitdata = { 1, 2, 3, 3 };
 
 static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 		       union _cpuid4_leaf_ebx *ebx,
@@ -493,8 +493,8 @@ static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
 	}
 }
 #else
-static void __init cache_shared_cpu_map_setup(unsigned int cpu, int index) {}
-static void __init cache_remove_shared_cpu_map(unsigned int cpu, int index) {}
+static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) {}
+static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index) {}
 #endif
 
 static void free_cache_attributes(unsigned int cpu)
@@ -794,8 +794,9 @@ static int __cpuinit cache_sysfs_init(void)
 	register_hotcpu_notifier(&cacheinfo_cpu_notifier);
 
 	for_each_online_cpu(i) {
-		cacheinfo_cpu_callback(&cacheinfo_cpu_notifier, CPU_ONLINE,
-			(void *)(long)i);
+		struct sys_device *sys_dev = get_cpu_sysdev((unsigned int)i);
+
+		cache_add_dev(sys_dev);
 	}
 
 	return 0;

arch/x86/kernel/cpu/mcheck/p4.c

@@ -61,6 +61,7 @@ fastcall void smp_thermal_interrupt(struct pt_regs *regs)
 {
 	irq_enter();
 	vendor_thermal_interrupt(regs);
+	__get_cpu_var(irq_stat).irq_thermal_count++;
 	irq_exit();
 }
 

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

@@ -152,7 +152,7 @@ static __cpuinit int thermal_throttle_cpu_callback(struct notifier_block *nfb,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block thermal_throttle_cpu_notifier =
+static struct notifier_block thermal_throttle_cpu_notifier __cpuinitdata =
 {
 	.notifier_call = thermal_throttle_cpu_callback,
 };

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

@@ -738,13 +738,7 @@ void mtrr_ap_init(void)
  */
 void mtrr_save_state(void)
 {
-	int cpu = get_cpu();
-
-	if (cpu == 0)
-		mtrr_save_fixed_ranges(NULL);
-	else
-		smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1);
-	put_cpu();
+	smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1);
 }
 
 static int __init mtrr_init_finialize(void)

arch/x86/kernel/cpu/perfctr-watchdog.c

@@ -34,7 +34,7 @@ struct wd_ops {
 	u64 checkbit;
 };
 
-static struct wd_ops *wd_ops;
+static const struct wd_ops *wd_ops;
 
 /* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
  * offset from MSR_P4_BSU_ESCR0.  It will be the max for all platforms (for now)
@@ -317,7 +317,7 @@ static void single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
 	write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
 }
 
-static struct wd_ops k7_wd_ops = {
+static const struct wd_ops k7_wd_ops = {
 	.reserve = single_msr_reserve,
 	.unreserve = single_msr_unreserve,
 	.setup = setup_k7_watchdog,
@@ -380,7 +380,7 @@ static void p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
 	write_watchdog_counter32(wd->perfctr_msr, NULL,nmi_hz);
 }
 
-static struct wd_ops p6_wd_ops = {
+static const struct wd_ops p6_wd_ops = {
 	.reserve = single_msr_reserve,
 	.unreserve = single_msr_unreserve,
 	.setup = setup_p6_watchdog,
@@ -532,7 +532,7 @@ static void p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
 	write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
 }
 
-static struct wd_ops p4_wd_ops = {
+static const struct wd_ops p4_wd_ops = {
 	.reserve = p4_reserve,
 	.unreserve = p4_unreserve,
 	.setup = setup_p4_watchdog,
@@ -550,6 +550,8 @@ static struct wd_ops p4_wd_ops = {
 #define ARCH_PERFMON_NMI_EVENT_SEL	ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
 #define ARCH_PERFMON_NMI_EVENT_UMASK	ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
 
+static struct wd_ops intel_arch_wd_ops;
+
 static int setup_intel_arch_watchdog(unsigned nmi_hz)
 {
 	unsigned int ebx;
@@ -591,11 +593,11 @@ static int setup_intel_arch_watchdog(unsigned nmi_hz)
 	wd->perfctr_msr = perfctr_msr;
 	wd->evntsel_msr = evntsel_msr;
 	wd->cccr_msr = 0;  //unused
-	wd_ops->checkbit = 1ULL << (eax.split.bit_width - 1);
+	intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1);
 	return 1;
 }
 
-static struct wd_ops intel_arch_wd_ops = {
+static struct wd_ops intel_arch_wd_ops __read_mostly = {
 	.reserve = single_msr_reserve,
 	.unreserve = single_msr_unreserve,
 	.setup = setup_intel_arch_watchdog,

arch/x86/kernel/cpuid.c

@@ -43,8 +43,6 @@
 
 static struct class *cpuid_class;
 
-#ifdef CONFIG_SMP
-
 struct cpuid_command {
 	u32 reg;
 	u32 *data;
@@ -62,25 +60,11 @@ static inline void do_cpuid(int cpu, u32 reg, u32 * data)
 {
 	struct cpuid_command cmd;
 
-	preempt_disable();
-	if (cpu == smp_processor_id()) {
-		cpuid(reg, &data[0], &data[1], &data[2], &data[3]);
-	} else {
-		cmd.reg = reg;
-		cmd.data = data;
+	cmd.reg = reg;
+	cmd.data = data;
 
-		smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1);
-	}
-	preempt_enable();
+	smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1);
 }
-#else				/* ! CONFIG_SMP */
-
-static inline void do_cpuid(int cpu, u32 reg, u32 * data)
-{
-	cpuid(reg, &data[0], &data[1], &data[2], &data[3]);
-}
-
-#endif				/* ! CONFIG_SMP */
 
 static loff_t cpuid_seek(struct file *file, loff_t offset, int orig)
 {
@@ -150,7 +134,7 @@ static const struct file_operations cpuid_fops = {
 	.open = cpuid_open,
 };
 
-static int cpuid_device_create(int i)
+static int __cpuinit cpuid_device_create(int i)
 {
 	int err = 0;
 	struct device *dev;
@@ -161,7 +145,9 @@ static int cpuid_device_create(int i)
 	return err;
 }
 
-static int cpuid_class_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
+static int __cpuinit cpuid_class_cpu_callback(struct notifier_block *nfb,
+					      unsigned long action,
+					      void *hcpu)
 {
 	unsigned int cpu = (unsigned long)hcpu;
 

arch/x86/kernel/entry_64.S

@@ -988,7 +988,7 @@ child_rip:
 	movq %rsi, %rdi
 	call *%rax
 	# exit
-	xorl %edi, %edi
+	mov %eax, %edi
 	call do_exit
 	CFI_ENDPROC
 ENDPROC(child_rip)

arch/x86/kernel/genapic_64.c

@@ -29,8 +29,6 @@ u8 x86_cpu_to_apicid[NR_CPUS] __read_mostly
 					= { [0 ... NR_CPUS-1] = BAD_APICID };
 EXPORT_SYMBOL(x86_cpu_to_apicid);
 
-u8 x86_cpu_to_log_apicid[NR_CPUS]	= { [0 ... NR_CPUS-1] = BAD_APICID };
-
 struct genapic __read_mostly *genapic = &apic_flat;
 
 /*

arch/x86/kernel/genapic_flat_64.c

@@ -52,7 +52,6 @@ static void flat_init_apic_ldr(void)
 
 	num = smp_processor_id();
 	id = 1UL << num;
-	x86_cpu_to_log_apicid[num] = id;
 	apic_write(APIC_DFR, APIC_DFR_FLAT);
 	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
 	val |= SET_APIC_LOGICAL_ID(id);

arch/x86/kernel/head_32.S

@@ -51,6 +51,15 @@
  */
 LOW_PAGES = 1<<(32-PAGE_SHIFT_asm)
 
+/*
+ * To preserve the DMA pool in PAGEALLOC kernels, we'll allocate
+ * pagetables from above the 16MB DMA limit, so we'll have to set
+ * up pagetables 16MB more (worst-case):
+ */
+#ifdef CONFIG_DEBUG_PAGEALLOC
+LOW_PAGES = LOW_PAGES + 0x1000000
+#endif
+
 #if PTRS_PER_PMD > 1
 PAGE_TABLE_SIZE = (LOW_PAGES / PTRS_PER_PMD) + PTRS_PER_PGD
 #else
@@ -443,6 +452,7 @@ early_page_fault:
 early_fault:
 	cld
 #ifdef CONFIG_PRINTK
+	pusha
 	movl $(__KERNEL_DS),%eax
 	movl %eax,%ds
 	movl %eax,%es
@@ -534,8 +544,15 @@ int_msg:
 	.asciz "Unknown interrupt or fault at EIP %p %p %p\n"
 
 fault_msg:
-	.ascii "Int %d: CR2 %p  err %p  EIP %p  CS %p  flags %p\n"
-	.asciz "Stack: %p %p %p %p %p %p %p %p\n"
+	.ascii								\
+/* fault info: */	"BUG: Int %d: CR2 %p\n"				\
+/* pusha regs: */	"     EDI %p  ESI %p  EBP %p  ESP %p\n"		\
+			"     EBX %p  EDX %p  ECX %p  EAX %p\n"		\
+/* fault frame: */	"     err %p  EIP %p   CS %p  flg %p\n"		\
+									\
+			"Stack: %p %p %p %p %p %p %p %p\n"		\
+			"       %p %p %p %p %p %p %p %p\n"		\
+			"       %p %p %p %p %p %p %p %p\n"
 
 #include "../../x86/xen/xen-head.S"
 

arch/x86/kernel/i386_ksyms_32.c

 #include <linux/module.h>
+#include <asm/semaphore.h>
 #include <asm/checksum.h>
 #include <asm/desc.h>
 

arch/x86/kernel/i8259_32.c

@@ -349,7 +349,11 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id)
  * New motherboards sometimes make IRQ 13 be a PCI interrupt,
  * so allow interrupt sharing.
  */
-static struct irqaction fpu_irq = { math_error_irq, 0, CPU_MASK_NONE, "fpu", NULL, NULL };
+static struct irqaction fpu_irq = {
+	.handler = math_error_irq,
+	.mask = CPU_MASK_NONE,
+	.name = "fpu",
+};
 
 void __init init_ISA_irqs (void)
 {

arch/x86/kernel/i8259_64.c

@@ -395,7 +395,11 @@ device_initcall(i8259A_init_sysfs);
  * IRQ2 is cascade interrupt to second interrupt controller
  */
 
-static struct irqaction irq2 = { no_action, 0, CPU_MASK_NONE, "cascade", NULL, NULL};
+static struct irqaction irq2 = {
+	.handler = no_action,
+	.mask = CPU_MASK_NONE,
+	.name = "cascade",
+};
 DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
 	[0 ... IRQ0_VECTOR - 1] = -1,
 	[IRQ0_VECTOR] = 0,

arch/x86/kernel/io_apic_32.c

@@ -1296,6 +1296,11 @@ static void __init setup_IO_APIC_irqs(void)
 			continue;
 		}
 
+		if (!first_notcon) {
+			apic_printk(APIC_VERBOSE, " not connected.\n");
+			first_notcon = 1;
+		}
+
 		entry.trigger = irq_trigger(idx);
 		entry.polarity = irq_polarity(idx);
 

arch/x86/kernel/io_apic_64.c

@@ -875,6 +875,10 @@ static void __init setup_IO_APIC_irqs(void)
 				apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mpc_apicid, pin);
 			continue;
 		}
+		if (!first_notcon) {
+			apic_printk(APIC_VERBOSE, " not connected.\n");
+			first_notcon = 1;
+		}
 
 		irq = pin_2_irq(idx, apic, pin);
 		add_pin_to_irq(irq, apic, pin);
@@ -885,7 +889,7 @@ static void __init setup_IO_APIC_irqs(void)
 	}
 
 	if (!first_notcon)
-		apic_printk(APIC_VERBOSE," not connected.\n");
+		apic_printk(APIC_VERBOSE, " not connected.\n");
 }
 
 /*
@@ -1845,7 +1849,7 @@ static struct sysdev_class ioapic_sysdev_class = {
 static int __init ioapic_init_sysfs(void)
 {
 	struct sys_device * dev;
-	int i, size, error = 0;
+	int i, size, error;
 
 	error = sysdev_class_register(&ioapic_sysdev_class);
 	if (error)
@@ -1854,12 +1858,11 @@ static int __init ioapic_init_sysfs(void)
 	for (i = 0; i < nr_ioapics; i++ ) {
 		size = sizeof(struct sys_device) + nr_ioapic_registers[i]
 			* sizeof(struct IO_APIC_route_entry);
-		mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL);
+		mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
 		if (!mp_ioapic_data[i]) {
 			printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
 			continue;
 		}
-		memset(mp_ioapic_data[i], 0, size);
 		dev = &mp_ioapic_data[i]->dev;
 		dev->id = i;
 		dev->cls = &ioapic_sysdev_class;

arch/x86/kernel/irq_32.c

@@ -255,9 +255,17 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 
 	if (i < NR_IRQS) {
+		unsigned any_count = 0;
+
 		spin_lock_irqsave(&irq_desc[i].lock, flags);
+#ifndef CONFIG_SMP
+		any_count = kstat_irqs(i);
+#else
+		for_each_online_cpu(j)
+			any_count |= kstat_cpu(j).irqs[i];
+#endif
 		action = irq_desc[i].action;
-		if (!action)
+		if (!action && !any_count)
 			goto skip;
 		seq_printf(p, "%3d: ",i);
 #ifndef CONFIG_SMP
@@ -268,10 +276,12 @@ int show_interrupts(struct seq_file *p, void *v)
 #endif
 		seq_printf(p, " %8s", irq_desc[i].chip->name);
 		seq_printf(p, "-%-8s", irq_desc[i].name);
-		seq_printf(p, "  %s", action->name);
 
-		for (action=action->next; action; action = action->next)
-			seq_printf(p, ", %s", action->name);
+		if (action) {
+			seq_printf(p, "  %s", action->name);
+			while ((action = action->next) != NULL)
+				seq_printf(p, ", %s", action->name);
+		}
 
 		seq_putc(p, '\n');
 skip:
@@ -280,14 +290,41 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "NMI: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", nmi_count(j));
-		seq_putc(p, '\n');
+		seq_printf(p, "  Non-maskable interrupts\n");
 #ifdef CONFIG_X86_LOCAL_APIC
 		seq_printf(p, "LOC: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ",
 				per_cpu(irq_stat,j).apic_timer_irqs);
-		seq_putc(p, '\n');
+		seq_printf(p, "  Local timer interrupts\n");
 #endif
+#ifdef CONFIG_SMP
+		seq_printf(p, "RES: ");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ",
+				per_cpu(irq_stat,j).irq_resched_count);
+		seq_printf(p, "  Rescheduling interrupts\n");
+		seq_printf(p, "CAL: ");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ",
+				per_cpu(irq_stat,j).irq_call_count);
+		seq_printf(p, "  function call interrupts\n");
+		seq_printf(p, "TLB: ");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ",
+				per_cpu(irq_stat,j).irq_tlb_count);
+		seq_printf(p, "  TLB shootdowns\n");
+#endif
+		seq_printf(p, "TRM: ");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ",
+				per_cpu(irq_stat,j).irq_thermal_count);
+		seq_printf(p, "  Thermal event interrupts\n");
+		seq_printf(p, "SPU: ");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ",
+				per_cpu(irq_stat,j).irq_spurious_count);
+		seq_printf(p, "  Spurious interrupts\n");
 		seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
 #if defined(CONFIG_X86_IO_APIC)
 		seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));

arch/x86/kernel/irq_64.c

@@ -62,9 +62,17 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 
 	if (i < NR_IRQS) {
+		unsigned any_count = 0;
+
 		spin_lock_irqsave(&irq_desc[i].lock, flags);
+#ifndef CONFIG_SMP
+		any_count = kstat_irqs(i);
+#else
+		for_each_online_cpu(j)
+			any_count |= kstat_cpu(j).irqs[i];
+#endif
 		action = irq_desc[i].action;
-		if (!action) 
+		if (!action && !any_count)
 			goto skip;
 		seq_printf(p, "%3d: ",i);
 #ifndef CONFIG_SMP
@@ -76,9 +84,11 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, " %8s", irq_desc[i].chip->name);
 		seq_printf(p, "-%-8s", irq_desc[i].name);
 
-		seq_printf(p, "  %s", action->name);
-		for (action=action->next; action; action = action->next)
-			seq_printf(p, ", %s", action->name);
+		if (action) {
+			seq_printf(p, "  %s", action->name);
+			while ((action = action->next) != NULL)
+				seq_printf(p, ", %s", action->name);
+		}
 		seq_putc(p, '\n');
 skip:
 		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
@@ -86,11 +96,37 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "NMI: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", cpu_pda(j)->__nmi_count);
-		seq_putc(p, '\n');
+		seq_printf(p, "  Non-maskable interrupts\n");
 		seq_printf(p, "LOC: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", cpu_pda(j)->apic_timer_irqs);
-		seq_putc(p, '\n');
+		seq_printf(p, "  Local timer interrupts\n");
+#ifdef CONFIG_SMP
+		seq_printf(p, "RES: ");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", cpu_pda(j)->irq_resched_count);
+		seq_printf(p, "  Rescheduling interrupts\n");
+		seq_printf(p, "CAL: ");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", cpu_pda(j)->irq_call_count);
+		seq_printf(p, "  function call interrupts\n");
+		seq_printf(p, "TLB: ");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", cpu_pda(j)->irq_tlb_count);
+		seq_printf(p, "  TLB shootdowns\n");
+#endif
+		seq_printf(p, "TRM: ");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", cpu_pda(j)->irq_thermal_count);
+		seq_printf(p, "  Thermal event interrupts\n");
+		seq_printf(p, "THR: ");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", cpu_pda(j)->irq_threshold_count);
+		seq_printf(p, "  Threshold APIC interrupts\n");
+		seq_printf(p, "SPU: ");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", cpu_pda(j)->irq_spurious_count);
+		seq_printf(p, "  Spurious interrupts\n");
 		seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
 	}
 	return 0;

arch/x86/kernel/ldt_32.c

@@ -92,13 +92,13 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	struct mm_struct * old_mm;
 	int retval = 0;
 
-	init_MUTEX(&mm->context.sem);
+	mutex_init(&mm->context.lock);
 	mm->context.size = 0;
 	old_mm = current->mm;
 	if (old_mm && old_mm->context.size > 0) {
-		down(&old_mm->context.sem);
+		mutex_lock(&old_mm->context.lock);
 		retval = copy_ldt(&mm->context, &old_mm->context);
-		up(&old_mm->context.sem);
+		mutex_unlock(&old_mm->context.lock);
 	}
 	return retval;
 }
@@ -130,7 +130,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount)
 	if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES)
 		bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES;
 
-	down(&mm->context.sem);
+	mutex_lock(&mm->context.lock);
 	size = mm->context.size*LDT_ENTRY_SIZE;
 	if (size > bytecount)
 		size = bytecount;
@@ -138,7 +138,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount)
 	err = 0;
 	if (copy_to_user(ptr, mm->context.ldt, size))
 		err = -EFAULT;
-	up(&mm->context.sem);
+	mutex_unlock(&mm->context.lock);
 	if (err < 0)
 		goto error_return;
 	if (size != bytecount) {
@@ -194,7 +194,7 @@ static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode)
 			goto out;
 	}
 
-	down(&mm->context.sem);
+	mutex_lock(&mm->context.lock);
 	if (ldt_info.entry_number >= mm->context.size) {
 		error = alloc_ldt(&current->mm->context, ldt_info.entry_number+1, 1);
 		if (error < 0)
@@ -221,7 +221,7 @@ static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode)
 	error = 0;
 
 out_unlock:
-	up(&mm->context.sem);
+	mutex_unlock(&mm->context.lock);
 out:
 	return error;
 }

arch/x86/kernel/ldt_64.c

@@ -96,13 +96,13 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	struct mm_struct * old_mm;
 	int retval = 0;
 
-	init_MUTEX(&mm->context.sem);
+	mutex_init(&mm->context.lock);
 	mm->context.size = 0;
 	old_mm = current->mm;
 	if (old_mm && old_mm->context.size > 0) {
-		down(&old_mm->context.sem);
+		mutex_lock(&old_mm->context.lock);
 		retval = copy_ldt(&mm->context, &old_mm->context);
-		up(&old_mm->context.sem);
+		mutex_unlock(&old_mm->context.lock);
 	}
 	return retval;
 }
@@ -133,7 +133,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount)
 	if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES)
 		bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES;
 
-	down(&mm->context.sem);
+	mutex_lock(&mm->context.lock);
 	size = mm->context.size*LDT_ENTRY_SIZE;
 	if (size > bytecount)
 		size = bytecount;
@@ -141,7 +141,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount)
 	err = 0;
 	if (copy_to_user(ptr, mm->context.ldt, size))
 		err = -EFAULT;
-	up(&mm->context.sem);
+	mutex_unlock(&mm->context.lock);
 	if (err < 0)
 		goto error_return;
 	if (size != bytecount) {
@@ -193,7 +193,7 @@ static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode)
 			goto out;
 	}
 
-	down(&mm->context.sem);
+	mutex_lock(&mm->context.lock);
 	if (ldt_info.entry_number >= (unsigned)mm->context.size) {
 		error = alloc_ldt(&current->mm->context, ldt_info.entry_number+1, 1);
 		if (error < 0)
@@ -223,7 +223,7 @@ static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode)
 	error = 0;
 
 out_unlock:
-	up(&mm->context.sem);
+	mutex_unlock(&mm->context.lock);
 out:
 	return error;
 }

arch/x86/kernel/mce_64.c

@@ -695,8 +695,6 @@ static int __init mcheck_disable(char *str)
    mce=nobootlog Don't log MCEs from before booting. */
 static int __init mcheck_enable(char *str)
 {
-	if (*str == '=')
-		str++;
 	if (!strcmp(str, "off"))
 		mce_dont_init = 1;
 	else if (!strcmp(str, "bootlog") || !strcmp(str,"nobootlog"))
@@ -709,7 +707,7 @@ static int __init mcheck_enable(char *str)
 }
 
 __setup("nomce", mcheck_disable);
-__setup("mce", mcheck_enable);
+__setup("mce=", mcheck_enable);
 
 /* 
  * Sysfs support

arch/x86/kernel/mce_amd_64.c

@@ -237,6 +237,7 @@ asmlinkage void mce_threshold_interrupt(void)
 		}
 	}
 out:
+	add_pda(irq_threshold_count, 1);
 	irq_exit();
 }
 

arch/x86/kernel/mce_intel_64.c

@@ -26,6 +26,7 @@ asmlinkage void smp_thermal_interrupt(void)
 	if (therm_throt_process(msr_val & 1))
 		mce_log_therm_throt_event(smp_processor_id(), msr_val);
 
+	add_pda(irq_thermal_count, 1);
 	irq_exit();
 }
 

arch/x86/kernel/msr.c

@@ -133,7 +133,7 @@ static const struct file_operations msr_fops = {
 	.open = msr_open,
 };
 
-static int msr_device_create(int i)
+static int __cpuinit msr_device_create(int i)
 {
 	int err = 0;
 	struct device *dev;
@@ -144,7 +144,7 @@ static int msr_device_create(int i)
 	return err;
 }
 
-static int msr_class_cpu_callback(struct notifier_block *nfb,
+static int __cpuinit msr_class_cpu_callback(struct notifier_block *nfb,
 				unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned long)hcpu;

arch/x86/kernel/pci-calgary_64.c

@@ -222,10 +222,10 @@ static inline unsigned int num_dma_pages(unsigned long dma, unsigned int dmalen)
 	return npages;
 }
 
-static inline int translate_phb(struct pci_dev* dev)
+static inline int translation_enabled(struct iommu_table *tbl)
 {
-	int disabled = bus_info[dev->bus->number].translation_disabled;
-	return !disabled;
+	/* only PHBs with translation enabled have an IOMMU table */
+	return (tbl != NULL);
 }
 
 static void iommu_range_reserve(struct iommu_table *tbl,
@@ -388,7 +388,7 @@ static void calgary_unmap_sg(struct device *dev,
 	struct scatterlist *s;
 	int i;
 
-	if (!translate_phb(to_pci_dev(dev)))
+	if (!translation_enabled(tbl))
 		return;
 
 	for_each_sg(sglist, s, nelems, i) {
@@ -428,7 +428,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 	unsigned long entry;
 	int i;
 
-	if (!translate_phb(to_pci_dev(dev)))
+	if (!translation_enabled(tbl))
 		return calgary_nontranslate_map_sg(dev, sg, nelems, direction);
 
 	for_each_sg(sg, s, nelems, i) {
@@ -474,7 +474,7 @@ static dma_addr_t calgary_map_single(struct device *dev, void *vaddr,
 	uaddr = (unsigned long)vaddr;
 	npages = num_dma_pages(uaddr, size);
 
-	if (translate_phb(to_pci_dev(dev)))
+	if (translation_enabled(tbl))
 		dma_handle = iommu_alloc(tbl, vaddr, npages, direction);
 	else
 		dma_handle = virt_to_bus(vaddr);
@@ -488,7 +488,7 @@ static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle,
 	struct iommu_table *tbl = find_iommu_table(dev);
 	unsigned int npages;
 
-	if (!translate_phb(to_pci_dev(dev)))
+	if (!translation_enabled(tbl))
 		return;
 
 	npages = num_dma_pages(dma_handle, size);
@@ -513,7 +513,7 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size,
 		goto error;
 	memset(ret, 0, size);
 
-	if (translate_phb(to_pci_dev(dev))) {
+	if (translation_enabled(tbl)) {
 		/* set up tces to cover the allocated range */
 		mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL);
 		if (mapping == bad_dma_address)
@@ -1194,7 +1194,7 @@ static int __init calgary_init(void)
 {
 	int ret;
 	struct pci_dev *dev = NULL;
-	void *tce_space;
+	struct calgary_bus_info *info;
 
 	ret = calgary_locate_bbars();
 	if (ret)
@@ -1206,12 +1206,14 @@ static int __init calgary_init(void)
 			break;
 		if (!is_cal_pci_dev(dev->device))
 			continue;
-		if (!translate_phb(dev)) {
+
+		info = &bus_info[dev->bus->number];
+		if (info->translation_disabled) {
 			calgary_init_one_nontraslated(dev);
 			continue;
 		}
-		tce_space = bus_info[dev->bus->number].tce_space;
-		if (!tce_space && !translate_empty_slots)
+
+		if (!info->tce_space && !translate_empty_slots)
 			continue;
 
 		ret = calgary_init_one(dev);
@@ -1229,11 +1231,13 @@ static int __init calgary_init(void)
 			break;
 		if (!is_cal_pci_dev(dev->device))
 			continue;
-		if (!translate_phb(dev)) {
+
+		info = &bus_info[dev->bus->number];
+		if (info->translation_disabled) {
 			pci_dev_put(dev);
 			continue;
 		}
-		if (!bus_info[dev->bus->number].tce_space && !translate_empty_slots)
+		if (!info->tce_space && !translate_empty_slots)
 			continue;
 
 		calgary_disable_translation(dev);
@@ -1546,7 +1550,7 @@ static void __init calgary_fixup_one_tce_space(struct pci_dev *dev)
 static int __init calgary_fixup_tce_spaces(void)
 {
 	struct pci_dev *dev = NULL;
-	void *tce_space;
+	struct calgary_bus_info *info;
 
 	if (no_iommu || swiotlb || !calgary_detected)
 		return -ENODEV;
@@ -1559,11 +1563,12 @@ static int __init calgary_fixup_tce_spaces(void)
 			break;
 		if (!is_cal_pci_dev(dev->device))
 			continue;
-		if (!translate_phb(dev))
+
+		info = &bus_info[dev->bus->number];
+		if (info->translation_disabled)
 			continue;
 
-		tce_space = bus_info[dev->bus->number].tce_space;
-		if (!tce_space)
+		if (!info->tce_space)
 			continue;
 
 		calgary_fixup_one_tce_space(dev);

arch/x86/kernel/pci-dma_32.c

@@ -12,7 +12,6 @@
 #include <linux/string.h>
 #include <linux/pci.h>
 #include <linux/module.h>
-#include <linux/pci.h>
 #include <asm/io.h>
 
 struct dma_coherent_mem {

arch/x86/kernel/pci-dma_64.c

@@ -51,11 +51,9 @@ dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order)
 {
 	struct page *page;
 	int node;
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type)
-		node = pcibus_to_node(to_pci_dev(dev)->bus);
-	else
-#endif
+
+	node = dev_to_node(dev);
+	if (node == -1)
 		node = numa_node_id();
 
 	if (node < first_node(node_online_map))

arch/x86/kernel/pci-gart_64.c

@@ -8,6 +8,7 @@
  * See Documentation/DMA-mapping.txt for the interface specification.
  * 
  * Copyright 2002 Andi Kleen, SuSE Labs.
+ * Subject to the GNU General Public License v2 only.
  */
 
 #include <linux/types.h>
@@ -375,7 +376,8 @@ static inline int dma_map_cont(struct scatterlist *start, int nelems,
  * DMA map all entries in a scatterlist.
  * Merge chunks that have page aligned sizes into a continuous mapping. 
  */
-int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
+static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+			int dir)
 {
 	int i;
 	int out;

arch/x86/kernel/ptrace_32.c

@@ -165,7 +165,7 @@ static unsigned long convert_eip_to_linear(struct task_struct *child, struct pt_
 
 		seg &= ~7UL;
 
-		down(&child->mm->context.sem);
+		mutex_lock(&child->mm->context.lock);
 		if (unlikely((seg >> 3) >= child->mm->context.size))
 			addr = -1L; /* bogus selector, access would fault */
 		else {
@@ -179,7 +179,7 @@ static unsigned long convert_eip_to_linear(struct task_struct *child, struct pt_
 				addr &= 0xffff;
 			addr += base;
 		}
-		up(&child->mm->context.sem);
+		mutex_unlock(&child->mm->context.lock);
 	}
 	return addr;
 }

arch/x86/kernel/ptrace_64.c

@@ -103,7 +103,7 @@ unsigned long convert_rip_to_linear(struct task_struct *child, struct pt_regs *r
 
 		seg &= ~7UL;
 
-		down(&child->mm->context.sem);
+		mutex_lock(&child->mm->context.lock);
 		if (unlikely((seg >> 3) >= child->mm->context.size))
 			addr = -1L; /* bogus selector, access would fault */
 		else {
@@ -117,7 +117,7 @@ unsigned long convert_rip_to_linear(struct task_struct *child, struct pt_regs *r
 				addr &= 0xffff;
 			addr += base;
 		}
-		up(&child->mm->context.sem);
+		mutex_unlock(&child->mm->context.lock);
 	}
 
 	return addr;

arch/x86/kernel/setup_64.c

@@ -604,7 +604,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	level = cpuid_eax(1);
 	if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58))
 		set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability);
-	if (c->x86 == 0x10)
+	if (c->x86 == 0x10 || c->x86 == 0x11)
 		set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability);
 
 	/* Enable workaround for FXSAVE leak */
@@ -968,7 +968,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	 * applications want to get the raw CPUID data, they should access
 	 * /dev/cpu/<cpu_nr>/cpuid instead.
 	 */
-	static char *x86_cap_flags[] = {
+	static const char *const x86_cap_flags[] = {
 		/* Intel-defined */
 	        "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
 	        "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",
@@ -1022,7 +1022,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 	};
-	static char *x86_power_flags[] = { 
+	static const char *const x86_power_flags[] = {
 		"ts",	/* temperature sensor */
 		"fid",  /* frequency id control */
 		"vid",  /* voltage id control */

arch/x86/kernel/signal_32.c

@@ -385,7 +385,6 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 	regs->edx = (unsigned long) 0;
 	regs->ecx = (unsigned long) 0;
 
-	set_fs(USER_DS);
 	regs->xds = __USER_DS;
 	regs->xes = __USER_DS;
 	regs->xss = __USER_DS;
@@ -479,7 +478,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	regs->edx = (unsigned long) &frame->info;
 	regs->ecx = (unsigned long) &frame->uc;
 
-	set_fs(USER_DS);
 	regs->xds = __USER_DS;
 	regs->xes = __USER_DS;
 	regs->xss = __USER_DS;

arch/x86/kernel/smp_32.c

@@ -342,6 +342,7 @@ fastcall void smp_invalidate_interrupt(struct pt_regs *regs)
 	smp_mb__after_clear_bit();
 out:
 	put_cpu_no_resched();
+	__get_cpu_var(irq_stat).irq_tlb_count++;
 }
 
 void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
@@ -640,6 +641,7 @@ static void native_smp_send_stop(void)
 fastcall void smp_reschedule_interrupt(struct pt_regs *regs)
 {
 	ack_APIC_irq();
+	__get_cpu_var(irq_stat).irq_resched_count++;
 }
 
 fastcall void smp_call_function_interrupt(struct pt_regs *regs)
@@ -660,6 +662,7 @@ fastcall void smp_call_function_interrupt(struct pt_regs *regs)
 	 */
 	irq_enter();
 	(*func)(info);
+	__get_cpu_var(irq_stat).irq_call_count++;
 	irq_exit();
 
 	if (wait) {
@@ -705,3 +708,10 @@ struct smp_ops smp_ops = {
 	.smp_send_reschedule = native_smp_send_reschedule,
 	.smp_call_function_mask = native_smp_call_function_mask,
 };
+
+int smp_call_function_mask(cpumask_t mask, void (*func) (void *info),
+			   void *info, int wait)
+{
+	return smp_ops.smp_call_function_mask(mask, func, info, wait);
+}
+EXPORT_SYMBOL(smp_call_function_mask);

arch/x86/kernel/smp_64.c

@@ -163,6 +163,7 @@ asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs)
 out:
 	ack_APIC_irq();
 	cpu_clear(cpu, f->flush_cpumask);
+	add_pda(irq_tlb_count, 1);
 }
 
 static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
@@ -493,6 +494,7 @@ void smp_send_stop(void)
 asmlinkage void smp_reschedule_interrupt(void)
 {
 	ack_APIC_irq();
+	add_pda(irq_resched_count, 1);
 }
 
 asmlinkage void smp_call_function_interrupt(void)
@@ -514,6 +516,7 @@ asmlinkage void smp_call_function_interrupt(void)
 	exit_idle();
 	irq_enter();
 	(*func)(info);
+	add_pda(irq_call_count, 1);
 	irq_exit();
 	if (wait) {
 		mb();

arch/x86/kernel/smpboot_32.c

@@ -102,8 +102,8 @@ u8 apicid_2_node[MAX_APICID];
  * Trampoline 80x86 program as an array.
  */
 
-extern unsigned char trampoline_data [];
-extern unsigned char trampoline_end  [];
+extern const unsigned char trampoline_data [];
+extern const unsigned char trampoline_end  [];
 static unsigned char *trampoline_base;
 static int trampoline_exec;
 
@@ -118,7 +118,7 @@ DEFINE_PER_CPU(int, cpu_state) = { 0 };
  * has made sure it's suitably aligned.
  */
 
-static unsigned long __devinit setup_trampoline(void)
+static unsigned long __cpuinit setup_trampoline(void)
 {
 	memcpy(trampoline_base, trampoline_data, trampoline_end - trampoline_data);
 	return virt_to_phys(trampoline_base);
@@ -1021,6 +1021,12 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 	if (!max_cpus) {
 		smp_found_config = 0;
 		printk(KERN_INFO "SMP mode deactivated, forcing use of dummy APIC emulation.\n");
+
+		if (nmi_watchdog == NMI_LOCAL_APIC) {
+			printk(KERN_INFO "activating minimal APIC for NMI watchdog use.\n");
+			connect_bsp_APIC();
+			setup_local_APIC();
+		}
 		smpboot_clear_io_apic_irqs();
 		phys_cpu_present_map = physid_mask_of_physid(0);
 		cpu_set(0, per_cpu(cpu_sibling_map, 0));

arch/x86/kernel/smpboot_64.c

@@ -102,8 +102,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map);
  * Trampoline 80x86 program as an array.
  */
 
-extern unsigned char trampoline_data[];
-extern unsigned char trampoline_end[];
+extern const unsigned char trampoline_data[];
+extern const unsigned char trampoline_end[];
 
 /* State of each CPU */
 DEFINE_PER_CPU(int, cpu_state) = { 0 };
@@ -695,7 +695,6 @@ static int __cpuinit do_boot_cpu(int cpu, int apicid)
 		cpu_clear(cpu, cpu_present_map);
 		cpu_clear(cpu, cpu_possible_map);
 		x86_cpu_to_apicid[cpu] = BAD_APICID;
-		x86_cpu_to_log_apicid[cpu] = BAD_APICID;
 		return -EIO;
 	}
 

arch/x86/kernel/stacktrace.c

@@ -33,7 +33,7 @@ static void save_stack_address(void *data, unsigned long addr)
 		trace->entries[trace->nr_entries++] = addr;
 }
 
-static struct stacktrace_ops save_stack_ops = {
+static const struct stacktrace_ops save_stack_ops = {
 	.warning = save_stack_warning,
 	.warning_symbol = save_stack_warning_symbol,
 	.stack = save_stack_stack,

arch/x86/kernel/tce_64.c

@@ -40,9 +40,9 @@ static inline void flush_tce(void* tceaddr)
 {
 	/* a single tce can't cross a cache line */
 	if (cpu_has_clflush)
-		asm volatile("clflush (%0)" :: "r" (tceaddr));
+		clflush(tceaddr);
 	else
-		asm volatile("wbinvd":::"memory");
+		wbinvd();
 }
 
 void tce_build(struct iommu_table *tbl, unsigned long index,

arch/x86/kernel/topology.c

@@ -44,15 +44,15 @@ int arch_register_cpu(int num)
 	 * Also certain PCI quirks require not to enable hotplug control
 	 * for all CPU's.
 	 */
-	if (num && enable_cpu_hotplug)
+#ifdef CONFIG_HOTPLUG_CPU
+	if (num)
 		cpu_devices[num].cpu.hotpluggable = 1;
+#endif
 
 	return register_cpu(&cpu_devices[num].cpu, num);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-int enable_cpu_hotplug = 1;
-
 void arch_unregister_cpu(int num) {
 	return unregister_cpu(&cpu_devices[num].cpu);
 }

arch/x86/kernel/trampoline_32.S

@@ -36,11 +36,11 @@
 #include <asm/segment.h>
 #include <asm/page.h>
 
-.data
-
 /* We can free up trampoline after bootup if cpu hotplug is not supported. */
 #ifndef CONFIG_HOTPLUG_CPU
 .section ".init.data","aw",@progbits
+#else
+.section .rodata,"a",@progbits
 #endif
 
 .code16

arch/x86/kernel/trampoline_64.S

@@ -33,7 +33,12 @@
 #include <asm/msr.h>
 #include <asm/segment.h>
 
-.data
+/* We can free up trampoline after bootup if cpu hotplug is not supported. */
+#ifndef CONFIG_HOTPLUG_CPU
+.section .init.data, "aw", @progbits
+#else
+.section .rodata, "a", @progbits
+#endif
 
 .code16
 

arch/x86/kernel/traps_32.c

@@ -112,7 +112,7 @@ struct stack_frame {
 
 static inline unsigned long print_context_stack(struct thread_info *tinfo,
 				unsigned long *stack, unsigned long ebp,
-				struct stacktrace_ops *ops, void *data)
+				const struct stacktrace_ops *ops, void *data)
 {
 #ifdef	CONFIG_FRAME_POINTER
 	struct stack_frame *frame = (struct stack_frame *)ebp;
@@ -149,7 +149,7 @@ static inline unsigned long print_context_stack(struct thread_info *tinfo,
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	        unsigned long *stack,
-		struct stacktrace_ops *ops, void *data)
+		const struct stacktrace_ops *ops, void *data)
 {
 	unsigned long ebp = 0;
 
@@ -221,7 +221,7 @@ static void print_trace_address(void *data, unsigned long addr)
 	touch_nmi_watchdog();
 }
 
-static struct stacktrace_ops print_trace_ops = {
+static const struct stacktrace_ops print_trace_ops = {
 	.warning = print_trace_warning,
 	.warning_symbol = print_trace_warning_symbol,
 	.stack = print_trace_stack,
@@ -398,31 +398,24 @@ void die(const char * str, struct pt_regs * regs, long err)
 		local_save_flags(flags);
 
 	if (++die.lock_owner_depth < 3) {
-		int nl = 0;
 		unsigned long esp;
 		unsigned short ss;
 
 		report_bug(regs->eip, regs);
 
-		printk(KERN_EMERG "%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter);
+		printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff,
+		       ++die_counter);
 #ifdef CONFIG_PREEMPT
-		printk(KERN_EMERG "PREEMPT ");
-		nl = 1;
+		printk("PREEMPT ");
 #endif
 #ifdef CONFIG_SMP
-		if (!nl)
-			printk(KERN_EMERG);
 		printk("SMP ");
-		nl = 1;
 #endif
 #ifdef CONFIG_DEBUG_PAGEALLOC
-		if (!nl)
-			printk(KERN_EMERG);
 		printk("DEBUG_PAGEALLOC");
-		nl = 1;
 #endif
-		if (nl)
-			printk("\n");
+		printk("\n");
+
 		if (notify_die(DIE_OOPS, str, regs, err,
 					current->thread.trap_no, SIGSEGV) !=
 				NOTIFY_STOP) {
@@ -1112,20 +1105,6 @@ asmlinkage void math_emulate(long arg)
 
 #endif /* CONFIG_MATH_EMULATION */
 
-#ifdef CONFIG_X86_F00F_BUG
-void __init trap_init_f00f_bug(void)
-{
-	__set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO);
-
-	/*
-	 * Update the IDT descriptor and reload the IDT so that
-	 * it uses the read-only mapped virtual address.
-	 */
-	idt_descr.address = fix_to_virt(FIX_F00F_IDT);
-	load_idt(&idt_descr);
-}
-#endif
-
 /*
  * This needs to use 'idt_table' rather than 'idt', and
  * thus use the _nonmapped_ version of the IDT, as the

arch/x86/kernel/traps_64.c

@@ -215,7 +215,7 @@ static inline int valid_stack_ptr(struct thread_info *tinfo, void *p)
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
 		unsigned long *stack,
-		struct stacktrace_ops *ops, void *data)
+		const struct stacktrace_ops *ops, void *data)
 {
 	const unsigned cpu = get_cpu();
 	unsigned long *irqstack_end = (unsigned long*)cpu_pda(cpu)->irqstackptr;
@@ -336,7 +336,7 @@ static void print_trace_address(void *data, unsigned long addr)
 	printk_address(addr);
 }
 
-static struct stacktrace_ops print_trace_ops = {
+static const struct stacktrace_ops print_trace_ops = {
 	.warning = print_trace_warning,
 	.warning_symbol = print_trace_warning_symbol,
 	.stack = print_trace_stack,

arch/x86/kernel/tsc_32.c

@@ -349,10 +349,10 @@ __cpuinit int unsynchronized_tsc(void)
 
 static void __init check_geode_tsc_reliable(void)
 {
-	unsigned long val;
+	unsigned long res_low, res_high;
 
-	rdmsrl(MSR_GEODE_BUSCONT_CONF0, val);
-	if ((val & RTSC_SUSP))
+	rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
+	if (res_low & RTSC_SUSP)
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
 }
 #else

arch/x86/kernel/vsyscall_64.c

@@ -78,7 +78,6 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
 	vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
 	vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
 	vsyscall_gtod_data.sys_tz = sys_tz;
-	vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
 	vsyscall_gtod_data.wall_to_monotonic = wall_to_monotonic;
 	write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
 }
@@ -289,7 +288,7 @@ static void __cpuinit vsyscall_set_cpu(int cpu)
 	unsigned long *d;
 	unsigned long node = 0;
 #ifdef CONFIG_NUMA
-	node = cpu_to_node[cpu];
+	node = cpu_to_node(cpu);
 #endif
 	if (cpu_has(&cpu_data[cpu], X86_FEATURE_RDTSCP))
 		write_rdtscp_aux((node << 12) | cpu);

arch/x86/lib/bitstr_64.c

@@ -14,7 +14,7 @@ find_next_zero_string(unsigned long *bitmap, long start, long nbits, int len)
 	
 	/* could test bitsliced, but it's hardly worth it */
 	end = n+len;
-	if (end >= nbits) 
+	if (end > nbits)
 		return -1; 
 	for (i = n+1; i < end; i++) { 
 		if (test_bit(i, bitmap)) {  

arch/x86/lib/msr-on-cpu.c

@@ -26,27 +26,18 @@ static void __rdmsr_safe_on_cpu(void *info)
 static int _rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h, int safe)
 {
 	int err = 0;
-	preempt_disable();
-	if (smp_processor_id() == cpu)
-		if (safe)
-			err = rdmsr_safe(msr_no, l, h);
-		else
-			rdmsr(msr_no, *l, *h);
-	else {
-		struct msr_info rv;
-
-		rv.msr_no = msr_no;
-		if (safe) {
-			smp_call_function_single(cpu, __rdmsr_safe_on_cpu,
-						 &rv, 0, 1);
-			err = rv.err;
-		} else {
-			smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 0, 1);
-		}
-		*l = rv.l;
-		*h = rv.h;
+	struct msr_info rv;
+
+	rv.msr_no = msr_no;
+	if (safe) {
+		smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 0, 1);
+		err = rv.err;
+	} else {
+		smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 0, 1);
 	}
-	preempt_enable();
+	*l = rv.l;
+	*h = rv.h;
+
 	return err;
 }
 
@@ -67,27 +58,18 @@ static void __wrmsr_safe_on_cpu(void *info)
 static int _wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h, int safe)
 {
 	int err = 0;
-	preempt_disable();
-	if (smp_processor_id() == cpu)
-		if (safe)
-			err = wrmsr_safe(msr_no, l, h);
-		else
-			wrmsr(msr_no, l, h);
-	else {
-		struct msr_info rv;
-
-		rv.msr_no = msr_no;
-		rv.l = l;
-		rv.h = h;
-		if (safe) {
-			smp_call_function_single(cpu, __wrmsr_safe_on_cpu,
-						 &rv, 0, 1);
-			err = rv.err;
-		} else {
-			smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 0, 1);
-		}
+	struct msr_info rv;
+
+	rv.msr_no = msr_no;
+	rv.l = l;
+	rv.h = h;
+	if (safe) {
+		smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 0, 1);
+		err = rv.err;
+	} else {
+		smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 0, 1);
 	}
-	preempt_enable();
+
 	return err;
 }
 

arch/x86/lib/rwlock_64.S

@@ -2,7 +2,7 @@
 
 #include <linux/linkage.h>
 #include <asm/rwlock.h>
-#include <asm/alternative-asm.i>
+#include <asm/alternative-asm.h>
 #include <asm/dwarf2.h>
 
 /* rdi:	pointer to rwlock_t */

arch/x86/lib/semaphore_32.S

@@ -15,8 +15,8 @@
 
 #include <linux/linkage.h>
 #include <asm/rwlock.h>
-#include <asm/alternative-asm.i>
-#include <asm/frame.i>
+#include <asm/alternative-asm.h>
+#include <asm/frame.h>
 #include <asm/dwarf2.h>
 
 /*

arch/x86/lib/string_32.c

@@ -160,26 +160,6 @@ char *strchr(const char * s, int c)
 EXPORT_SYMBOL(strchr);
 #endif
 
-#ifdef __HAVE_ARCH_STRRCHR
-char *strrchr(const char * s, int c)
-{
-	int d0, d1;
-	char * res;
-	asm volatile( "movb %%al,%%ah\n"
-		"1:\tlodsb\n\t"
-		"cmpb %%ah,%%al\n\t"
-		"jne 2f\n\t"
-		"leal -1(%%esi),%0\n"
-		"2:\ttestb %%al,%%al\n\t"
-		"jne 1b"
-		:"=g" (res), "=&S" (d0), "=&a" (d1)
-		:"0" (0),"1" (s),"2" (c)
-		:"memory");
-	return res;
-}
-EXPORT_SYMBOL(strrchr);
-#endif
-
 #ifdef __HAVE_ARCH_STRLEN
 size_t strlen(const char * s)
 {

arch/x86/mach-default/setup.c

@@ -35,7 +35,11 @@ void __init pre_intr_init_hook(void)
 /*
  * IRQ2 is cascade interrupt to second interrupt controller
  */
-static struct irqaction irq2 = { no_action, 0, CPU_MASK_NONE, "cascade", NULL, NULL};
+static struct irqaction irq2 = {
+	.handler = no_action,
+	.mask = CPU_MASK_NONE,
+	.name = "cascade",
+};
 
 /**
  * intr_init_hook - post gate setup interrupt initialisation

arch/x86/mach-es7000/es7000plat.c

@@ -46,11 +46,11 @@
  * ES7000 Globals
  */
 
-volatile unsigned long	*psai = NULL;
-struct mip_reg		*mip_reg;
-struct mip_reg		*host_reg;
-int 			mip_port;
-unsigned long		mip_addr, host_addr;
+static volatile unsigned long	*psai = NULL;
+static struct mip_reg		*mip_reg;
+static struct mip_reg		*host_reg;
+static int 			mip_port;
+static unsigned long		mip_addr, host_addr;
 
 /*
  * GSI override for ES7000 platforms.
@@ -288,28 +288,8 @@ es7000_start_cpu(int cpu, unsigned long eip)
 
 }
 
-int
-es7000_stop_cpu(int cpu)
-{
-	int startup;
-
-	if (psai == NULL)
-		return -1;
-
-	startup= (0x1000000 | cpu);
-
-	while ((*psai & 0xff00ffff) != startup)
-		;
-
-	startup = (*psai & 0xff0000) >> 16;
-	*psai &= 0xffffff;
-
-	return 0;
-
-}
-
 void __init
-es7000_sw_apic()
+es7000_sw_apic(void)
 {
 	if (es7000_plat) {
 		int mip_status;

arch/x86/mach-generic/probe.c

@@ -22,7 +22,7 @@ extern struct genapic apic_default;
 
 struct genapic *genapic = &apic_default;
 
-struct genapic *apic_probe[] __initdata = { 
+static struct genapic *apic_probe[] __initdata = {
 	&apic_summit,
 	&apic_bigsmp, 
 	&apic_es7000,

arch/x86/mach-voyager/setup.c

@@ -18,7 +18,11 @@ void __init pre_intr_init_hook(void)
 /*
  * IRQ2 is cascade interrupt to second interrupt controller
  */
-static struct irqaction irq2 = { no_action, 0, CPU_MASK_NONE, "cascade", NULL, NULL};
+static struct irqaction irq2 = {
+	.handler = no_action,
+	.mask = CPU_MASK_NONE,
+	.name = "cascade",
+};
 
 void __init intr_init_hook(void)
 {

arch/x86/mach-voyager/voyager_smp.c

@@ -442,8 +442,8 @@ static __u32 __init
 setup_trampoline(void)
 {
 	/* these two are global symbols in trampoline.S */
-	extern __u8 trampoline_end[];
-	extern __u8 trampoline_data[];
+	extern const __u8 trampoline_end[];
+	extern const __u8 trampoline_data[];
 
 	memcpy((__u8 *)trampoline_base, trampoline_data,
 	       trampoline_end - trampoline_data);
@@ -1037,6 +1037,7 @@ smp_call_function_interrupt(void)
 	 */
 	irq_enter();
 	(*func)(info);
+	__get_cpu_var(irq_stat).irq_call_count++;
 	irq_exit();
 	if (wait) {
 		mb();

arch/x86/mm/discontig_32.c

@@ -103,14 +103,14 @@ extern unsigned long highend_pfn, highstart_pfn;
 
 #define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE)
 
-unsigned long node_remap_start_pfn[MAX_NUMNODES];
+static unsigned long node_remap_start_pfn[MAX_NUMNODES];
 unsigned long node_remap_size[MAX_NUMNODES];
-unsigned long node_remap_offset[MAX_NUMNODES];
-void *node_remap_start_vaddr[MAX_NUMNODES];
+static unsigned long node_remap_offset[MAX_NUMNODES];
+static void *node_remap_start_vaddr[MAX_NUMNODES];
 void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
-void *node_remap_end_vaddr[MAX_NUMNODES];
-void *node_remap_alloc_vaddr[MAX_NUMNODES];
+static void *node_remap_end_vaddr[MAX_NUMNODES];
+static void *node_remap_alloc_vaddr[MAX_NUMNODES];
 static unsigned long kva_start_pfn;
 static unsigned long kva_pages;
 /*

arch/x86/mm/fault_32.c

@@ -105,7 +105,7 @@ static inline unsigned long get_segment_eip(struct pt_regs *regs,
 	   LDT and other horrors are only used in user space. */
 	if (seg & (1<<2)) {
 		/* Must lock the LDT while reading it. */
-		down(&current->mm->context.sem);
+		mutex_lock(&current->mm->context.lock);
 		desc = current->mm->context.ldt;
 		desc = (void *)desc + (seg & ~7);
 	} else {
@@ -118,7 +118,7 @@ static inline unsigned long get_segment_eip(struct pt_regs *regs,
 	base = get_desc_base((unsigned long *)desc);
 
 	if (seg & (1<<2)) { 
-		up(&current->mm->context.sem);
+		mutex_unlock(&current->mm->context.lock);
 	} else
 		put_cpu();
 
@@ -539,23 +539,22 @@ fastcall void __kprobes do_page_fault(struct pt_regs *regs,
 			printk(KERN_ALERT "BUG: unable to handle kernel paging"
 					" request");
 		printk(" at virtual address %08lx\n",address);
-		printk(KERN_ALERT " printing eip:\n");
-		printk("%08lx\n", regs->eip);
+		printk(KERN_ALERT "printing eip: %08lx ", regs->eip);
 
 		page = read_cr3();
 		page = ((__typeof__(page) *) __va(page))[address >> PGDIR_SHIFT];
 #ifdef CONFIG_X86_PAE
-		printk(KERN_ALERT "*pdpt = %016Lx\n", page);
+		printk("*pdpt = %016Lx ", page);
 		if ((page >> PAGE_SHIFT) < max_low_pfn
 		    && page & _PAGE_PRESENT) {
 			page &= PAGE_MASK;
 			page = ((__typeof__(page) *) __va(page))[(address >> PMD_SHIFT)
 			                                         & (PTRS_PER_PMD - 1)];
-			printk(KERN_ALERT "*pde = %016Lx\n", page);
+			printk(KERN_ALERT "*pde = %016Lx ", page);
 			page &= ~_PAGE_NX;
 		}
 #else
-		printk(KERN_ALERT "*pde = %08lx\n", page);
+		printk("*pde = %08lx ", page);
 #endif
 
 		/*
@@ -569,8 +568,10 @@ fastcall void __kprobes do_page_fault(struct pt_regs *regs,
 			page &= PAGE_MASK;
 			page = ((__typeof__(page) *) __va(page))[(address >> PAGE_SHIFT)
 			                                         & (PTRS_PER_PTE - 1)];
-			printk(KERN_ALERT "*pte = %0*Lx\n", sizeof(page)*2, (u64)page);
+			printk("*pte = %0*Lx ", sizeof(page)*2, (u64)page);
 		}
+
+		printk("\n");
 	}
 
 	tsk->thread.cr2 = address;

arch/x86/mm/init_32.c

@@ -85,13 +85,20 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 static pte_t * __init one_page_table_init(pmd_t *pmd)
 {
 	if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
-		pte_t *page_table = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+		pte_t *page_table = NULL;
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+		page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
+#endif
+		if (!page_table)
+			page_table =
+				(pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
 
 		paravirt_alloc_pt(&init_mm, __pa(page_table) >> PAGE_SHIFT);
 		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
 		BUG_ON(page_table != pte_offset_kernel(pmd, 0));
 	}
-	
+
 	return pte_offset_kernel(pmd, 0);
 }
 

arch/x86/mm/numa_64.c

@@ -166,7 +166,7 @@ early_node_mem(int nodeid, unsigned long start, unsigned long end,
 		return __va(mem);
 	ptr = __alloc_bootmem_nopanic(size,
 				SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS));
-	if (ptr == 0) {
+	if (ptr == NULL) {
 		printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
 			size, nodeid);
 		return NULL;
@@ -261,7 +261,7 @@ void __init numa_init_array(void)
 	   We round robin the existing nodes. */
 	rr = first_node(node_online_map);
 	for (i = 0; i < NR_CPUS; i++) {
-		if (cpu_to_node[i] != NUMA_NO_NODE)
+		if (cpu_to_node(i) != NUMA_NO_NODE)
 			continue;
  		numa_set_node(i, rr);
 		rr = next_node(rr, node_online_map);
@@ -543,7 +543,7 @@ __cpuinit void numa_add_cpu(int cpu)
 void __cpuinit numa_set_node(int cpu, int node)
 {
 	cpu_pda(cpu)->nodenumber = node;
-	cpu_to_node[cpu] = node;
+	cpu_to_node(cpu) = node;
 }
 
 unsigned long __init numa_free_all_bootmem(void) 

arch/x86/mm/pageattr_32.c

@@ -70,10 +70,10 @@ static struct page *split_large_page(unsigned long address, pgprot_t prot,
 
 static void cache_flush_page(struct page *p)
 { 
-	unsigned long adr = (unsigned long)page_address(p);
+	void *adr = page_address(p);
 	int i;
 	for (i = 0; i < PAGE_SIZE; i += boot_cpu_data.x86_clflush_size)
-		asm volatile("clflush (%0)" :: "r" (adr + i));
+		clflush(adr+i);
 }
 
 static void flush_kernel_map(void *arg)

arch/x86/mm/pageattr_64.c

@@ -65,7 +65,7 @@ static void cache_flush_page(void *adr)
 {
 	int i;
 	for (i = 0; i < PAGE_SIZE; i += boot_cpu_data.x86_clflush_size)
-		asm volatile("clflush (%0)" :: "r" (adr + i));
+		clflush(adr+i);
 }
 
 static void flush_kernel_map(void *arg)
@@ -148,6 +148,7 @@ __change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot,
 			split = split_large_page(address, prot, ref_prot2);
 			if (!split)
 				return -ENOMEM;
+			pgprot_val(ref_prot2) &= ~_PAGE_NX;
 			set_pte(kpte, mk_pte(split, ref_prot2));
 			kpte_page = split;
 		}

arch/x86/mm/pgtable_32.c

@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/mm.h>
+#include <linux/nmi.h>
 #include <linux/swap.h>
 #include <linux/smp.h>
 #include <linux/highmem.h>
@@ -39,6 +40,8 @@ void show_mem(void)
 	for_each_online_pgdat(pgdat) {
 		pgdat_resize_lock(pgdat, &flags);
 		for (i = 0; i < pgdat->node_spanned_pages; ++i) {
+			if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
+				touch_nmi_watchdog();
 			page = pgdat_page_nr(pgdat, i);
 			total++;
 			if (PageHighMem(page))
@@ -97,8 +100,7 @@ static void set_pte_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
 	}
 	pte = pte_offset_kernel(pmd, vaddr);
 	if (pgprot_val(flags))
-		/* <pfn,flags> stored as-is, to permit clearing entries */
-		set_pte(pte, pfn_pte(pfn, flags));
+		set_pte_present(&init_mm, vaddr, pte, pfn_pte(pfn, flags));
 	else
 		pte_clear(&init_mm, vaddr, pte);
 

arch/x86/mm/srat_64.c

@@ -431,9 +431,9 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 			setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 
 	for (i = 0; i < NR_CPUS; i++) {
-		if (cpu_to_node[i] == NUMA_NO_NODE)
+		if (cpu_to_node(i) == NUMA_NO_NODE)
 			continue;
-		if (!node_isset(cpu_to_node[i], node_possible_map))
+		if (!node_isset(cpu_to_node(i), node_possible_map))
 			numa_set_node(i, NUMA_NO_NODE);
 	}
 	numa_init_array();

arch/x86/oprofile/nmi_int.c

@@ -269,7 +269,6 @@ static void nmi_cpu_shutdown(void * dummy)
 	apic_write(APIC_LVTPC, saved_lvtpc[cpu]);
 	apic_write(APIC_LVTERR, v);
 	nmi_restore_registers(msrs);
-	model->shutdown(msrs);
 }
 
  
@@ -278,6 +277,7 @@ static void nmi_shutdown(void)
 	nmi_enabled = 0;
 	on_each_cpu(nmi_cpu_shutdown, NULL, 0, 1);
 	unregister_die_notifier(&profile_exceptions_nb);
+	model->shutdown(cpu_msrs);
 	free_msrs();
 }
 

arch/x86/pci/common.c

@@ -289,6 +289,22 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant BL685c G1"),
 		},
 	},
+	{
+		.callback = set_bf_sort,
+		.ident = "HP ProLiant DL385 G2",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"),
+		},
+	},
+	{
+		.callback = set_bf_sort,
+		.ident = "HP ProLiant DL585 G2",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"),
+		},
+	},
 #ifdef __i386__
 	{
 		.callback = assign_all_busses,

arch/x86/vdso/Makefile

@@ -13,7 +13,7 @@ vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
 
 $(obj)/vdso.o: $(obj)/vdso.so
 
-targets += vdso.so vdso.lds $(vobjs-y) vdso-syms.o
+targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y) vdso-syms.o
 
 # The DSO images are built using a special linker script.
 quiet_cmd_syscall = SYSCALL $@
@@ -26,12 +26,19 @@ vdso-flags = -fPIC -shared -Wl,-soname=linux-vdso.so.1 \
 		 $(call ld-option, -Wl$(comma)--hash-style=sysv) \
 		-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
 SYSCFLAGS_vdso.so = $(vdso-flags)
+SYSCFLAGS_vdso.so.dbg = $(vdso-flags)
 
 $(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
 
 $(obj)/vdso.so: $(src)/vdso.lds $(vobjs) FORCE
+
+$(obj)/vdso.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,syscall)
 
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
 CFL := $(PROFILING) -mcmodel=small -fPIC -g0 -O2 -fasynchronous-unwind-tables -m64
 
 $(obj)/vclock_gettime.o: KBUILD_CFLAGS = $(CFL)
@@ -47,3 +54,11 @@ $(obj)/built-in.o: ld_flags += -R $(obj)/vdso-syms.o
 SYSCFLAGS_vdso-syms.o = -r -d
 $(obj)/vdso-syms.o: $(src)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,syscall)
+
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+vdso.so:
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+vdso_install: vdso.so

arch/x86/vdso/vdso.lds.S

@@ -26,13 +26,16 @@ SECTIONS
      is insufficient, ld -shared will barf.  Just increase it here.  */
   . = VDSO_PRELINK + VDSO_TEXT_OFFSET;
 
-  .text           : { *(.text) }		:text
-  .text.ptr       : { *(.text.ptr) }		:text
-  . = VDSO_PRELINK + 0x900;
-  .data           : { *(.data) }		:text
-  .bss            : { *(.bss) }			:text
+  .text           : { *(.text*) }		:text
+  .rodata         : { *(.rodata*) }		:text
+  .data		  : {
+	*(.data*)
+	*(.sdata*)
+	*(.bss*)
+	*(.dynbss*)
+  }						:text
 
-  .altinstructions : { *(.altinstructions) }			:text
+  .altinstructions : { *(.altinstructions) }		:text
   .altinstr_replacement  : { *(.altinstr_replacement) }	:text
 
   .note		  : { *(.note.*) }		:text :note
@@ -42,7 +45,6 @@ SECTIONS
   .useless        : {
   	*(.got.plt) *(.got)
 	*(.gnu.linkonce.d.*)
-	*(.dynbss)
 	*(.gnu.linkonce.b.*)
   }						:text
 }

arch/x86/vdso/vvar.c

@@ -8,5 +8,5 @@
 #include <asm/timex.h>
 #include <asm/vgtod.h>
 
-#define VEXTERN(x) typeof (__ ## x) *vdso_ ## x = (void *)VMAGIC;
+#define VEXTERN(x) typeof (__ ## x) *const vdso_ ## x = (void *)VMAGIC;
 #include "vextern.h"

arch/x86/xen/smp.c

@@ -356,6 +356,7 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
 	 */
 	irq_enter();
 	(*func)(info);
+	__get_cpu_var(irq_stat).irq_call_count++;
 	irq_exit();
 
 	if (wait) {

arch/x86_64/Kconfig

@@ -175,14 +175,12 @@ config MK8
 config MPSC
        bool "Intel P4 / older Netburst based Xeon"
        help
-	  Optimize for Intel Pentium 4 and older Nocona/Dempsey Xeon CPUs
-	  with Intel Extended Memory 64 Technology(EM64T). For details see
-	  <http://www.intel.com/technology/64bitextensions/>.
+	  Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey
+	  Xeon CPUs with Intel 64bit which is compatible with x86-64.
 	  Note that the latest Xeons (Xeon 51xx and 53xx) are not based on the
           Netburst core and shouldn't use this option. You can distinguish them
 	  using the cpu family field
-	  in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one
-	  (this rule only applies to systems that support EM64T)
+	  in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one.
 
 config MCORE2
 	bool "Intel Core2 / newer Xeon"
@@ -190,8 +188,7 @@ config MCORE2
 	  Optimize for Intel Core2 and newer Xeons (51xx)
 	  You can distinguish the newer Xeons from the older ones using
 	  the cpu family field in /proc/cpuinfo. 15 is an older Xeon
-	  (use CONFIG_MPSC then), 6 is a newer one. This rule only
-	  applies to CPUs that support EM64T.
+	  (use CONFIG_MPSC then), 6 is a newer one.
 
 config GENERIC_CPU
 	bool "Generic-x86-64"
@@ -476,8 +473,9 @@ config HPET_TIMER
 	  <http://www.intel.com/hardwaredesign/hpetspec.htm>.
 
 config HPET_EMULATE_RTC
-	bool "Provide RTC interrupt"
+	bool
 	depends on HPET_TIMER && RTC=y
+	default y
 
 # Mark as embedded because too many people got it wrong.
 # The code disables itself when not needed.

arch/x86_64/Makefile

@@ -110,9 +110,15 @@ bzdisk: vmlinux
 fdimage fdimage144 fdimage288 isoimage: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) $@
 
-install:
+install: vdso_install
 	$(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) $@ 
 
+vdso_install:
+ifeq ($(CONFIG_IA32_EMULATION),y)
+	$(Q)$(MAKE) $(build)=arch/x86/ia32 $@
+endif
+	$(Q)$(MAKE) $(build)=arch/x86/vdso $@
+
 archclean:
 	$(Q)rm -rf $(objtree)/arch/x86_64/boot
 	$(Q)$(MAKE) $(clean)=$(boot)

drivers/char/agp/efficeon-agp.c

@@ -221,7 +221,7 @@ static int efficeon_create_gatt_table(struct agp_bridge_data *bridge)
 		SetPageReserved(virt_to_page((char *)page));
 
 		for (offset = 0; offset < PAGE_SIZE; offset += clflush_chunk)
-			asm volatile("clflush %0" : : "m" (*(char *)(page+offset)));
+			clflush((char *)page+offset);
 
 		efficeon_private.l1_table[index] = page;
 
@@ -268,15 +268,16 @@ static int efficeon_insert_memory(struct agp_memory * mem, off_t pg_start, int t
 		*page = insert;
 
 		/* clflush is slow, so don't clflush until we have to */
-		if ( last_page &&
-		     ((unsigned long)page^(unsigned long)last_page) & clflush_mask )
-		    asm volatile("clflush %0" : : "m" (*last_page));
+		if (last_page &&
+		    (((unsigned long)page^(unsigned long)last_page) &
+		     clflush_mask))
+			clflush(last_page);
 
 		last_page = page;
 	}
 
 	if ( last_page )
-		asm volatile("clflush %0" : : "m" (*last_page));
+		clflush(last_page);
 
 	agp_bridge->driver->tlb_flush(mem);
 	return 0;

drivers/video/Kconfig

@@ -15,7 +15,6 @@ config VGASTATE
 
 config VIDEO_OUTPUT_CONTROL
 	tristate "Lowlevel video output switch controls"
-	default m
 	help
 	  This framework adds support for low-level control of the video 
 	  output switch.

include/asm-um/alternative-asm.i → include/asm-um/alternative-asm.h

 #ifndef __UM_ALTERNATIVE_ASM_I
 #define __UM_ALTERNATIVE_ASM_I
 
-#include "asm/arch/alternative-asm.i"
+#include "asm/arch/alternative-asm.h"
 
 #endif

include/asm-um/frame.i → include/asm-um/frame.h

 #ifndef __UM_FRAME_I
 #define __UM_FRAME_I
 
-#include "asm/arch/frame.i"
+#include "asm/arch/frame.h"
 
 #endif

include/asm-x86/Kbuild

 include include/asm-generic/Kbuild.asm
 
 header-y += boot.h
-header-y += debugreg_32.h
-header-y += debugreg_64.h
 header-y += debugreg.h
-header-y += ldt_32.h
-header-y += ldt_64.h
 header-y += ldt.h
 header-y += msr-index.h
 header-y += prctl.h
-header-y += ptrace-abi_32.h
-header-y += ptrace-abi_64.h
 header-y += ptrace-abi.h
 header-y += sigcontext32.h
-header-y += ucontext_32.h
-header-y += ucontext_64.h
 header-y += ucontext.h
 header-y += vsyscall32.h
 
 unifdef-y += a.out_32.h
 unifdef-y += a.out_64.h
-unifdef-y += auxvec_32.h
-unifdef-y += auxvec_64.h
 unifdef-y += byteorder_32.h
 unifdef-y += byteorder_64.h
 unifdef-y += elf_32.h
 unifdef-y += elf_64.h
-unifdef-y += errno_32.h
-unifdef-y += errno_64.h
-unifdef-y += ioctls_32.h
-unifdef-y += ioctls_64.h
-unifdef-y += ipcbuf_32.h
-unifdef-y += ipcbuf_64.h
 unifdef-y += mce.h
-unifdef-y += mman_32.h
-unifdef-y += mman_64.h
 unifdef-y += msgbuf_32.h
 unifdef-y += msgbuf_64.h
 unifdef-y += msr_32.h
@@ -45,40 +27,22 @@ unifdef-y += mtrr_64.h
 unifdef-y += mtrr.h
 unifdef-y += page_32.h
 unifdef-y += page_64.h
-unifdef-y += param_32.h
-unifdef-y += param_64.h
 unifdef-y += posix_types_32.h
 unifdef-y += posix_types_64.h
 unifdef-y += ptrace_32.h
 unifdef-y += ptrace_64.h
-unifdef-y += resource_32.h
-unifdef-y += resource_64.h
-unifdef-y += sembuf_32.h
-unifdef-y += sembuf_64.h
 unifdef-y += setup_32.h
 unifdef-y += setup_64.h
 unifdef-y += shmbuf_32.h
 unifdef-y += shmbuf_64.h
-unifdef-y += shmparam_32.h
-unifdef-y += shmparam_64.h
 unifdef-y += sigcontext_32.h
 unifdef-y += sigcontext_64.h
-unifdef-y += siginfo_32.h
-unifdef-y += siginfo_64.h
 unifdef-y += signal_32.h
 unifdef-y += signal_64.h
-unifdef-y += sockios_32.h
-unifdef-y += sockios_64.h
 unifdef-y += stat_32.h
 unifdef-y += stat_64.h
 unifdef-y += statfs_32.h
 unifdef-y += statfs_64.h
-unifdef-y += termbits_32.h
-unifdef-y += termbits_64.h
-unifdef-y += termios_32.h
-unifdef-y += termios_64.h
-unifdef-y += types_32.h
-unifdef-y += types_64.h
 unifdef-y += unistd_32.h
 unifdef-y += unistd_64.h
 unifdef-y += user_32.h

include/asm-x86/agp.h

-#ifdef CONFIG_X86_32
-# include "agp_32.h"
-#else
-# include "agp_64.h"
+#ifndef _ASM_X86_AGP_H
+#define _ASM_X86_AGP_H
+
+#include <asm/pgtable.h>
+#include <asm/cacheflush.h>
+
+/*
+ * Functions to keep the agpgart mappings coherent with the MMU. The
+ * GART gives the CPU a physical alias of pages in memory. The alias
+ * region is mapped uncacheable. Make sure there are no conflicting
+ * mappings with different cachability attributes for the same
+ * page. This avoids data corruption on some CPUs.
+ */
+
+/*
+ * Caller's responsibility to call global_flush_tlb() for performance
+ * reasons
+ */
+#define map_page_into_agp(page) change_page_attr(page, 1, PAGE_KERNEL_NOCACHE)
+#define unmap_page_from_agp(page) change_page_attr(page, 1, PAGE_KERNEL)
+#define flush_agp_mappings() global_flush_tlb()
+
+/*
+ * Could use CLFLUSH here if the cpu supports it. But then it would
+ * need to be called for each cacheline of the whole page so it may
+ * not be worth it. Would need a page for it.
+ */
+#define flush_agp_cache() wbinvd()
+
+/* Convert a physical address to an address suitable for the GART. */
+#define phys_to_gart(x) (x)
+#define gart_to_phys(x) (x)
+
+/* GATT allocation. Returns/accepts GATT kernel virtual address. */
+#define alloc_gatt_pages(order)		\
+	((char *)__get_free_pages(GFP_KERNEL, (order)))
+#define free_gatt_pages(table, order)	\
+	free_pages((unsigned long)(table), (order))
+
 #endif

include/asm-x86/agp_32.h

-#ifndef AGP_H
-#define AGP_H 1
-
-#include <asm/pgtable.h>
-#include <asm/cacheflush.h>
-
-/* 
- * Functions to keep the agpgart mappings coherent with the MMU.
- * The GART gives the CPU a physical alias of pages in memory. The alias region is
- * mapped uncacheable. Make sure there are no conflicting mappings
- * with different cachability attributes for the same page. This avoids
- * data corruption on some CPUs.
- */
-
-/* Caller's responsibility to call global_flush_tlb() for
- * performance reasons */
-#define map_page_into_agp(page) change_page_attr(page, 1, PAGE_KERNEL_NOCACHE)
-#define unmap_page_from_agp(page) change_page_attr(page, 1, PAGE_KERNEL)
-#define flush_agp_mappings() global_flush_tlb()
-
-/* Could use CLFLUSH here if the cpu supports it. But then it would
-   need to be called for each cacheline of the whole page so it may not be 
-   worth it. Would need a page for it. */
-#define flush_agp_cache() wbinvd()
-
-/* Convert a physical address to an address suitable for the GART. */
-#define phys_to_gart(x) (x)
-#define gart_to_phys(x) (x)
-
-/* GATT allocation. Returns/accepts GATT kernel virtual address. */
-#define alloc_gatt_pages(order)		\
-	((char *)__get_free_pages(GFP_KERNEL, (order)))
-#define free_gatt_pages(table, order)	\
-	free_pages((unsigned long)(table), (order))
-
-#endif

include/asm-x86/agp_64.h

-#ifndef AGP_H
-#define AGP_H 1
-
-#include <asm/cacheflush.h>
-
-/* 
- * Functions to keep the agpgart mappings coherent.
- * The GART gives the CPU a physical alias of memory. The alias is
- * mapped uncacheable. Make sure there are no conflicting mappings
- * with different cachability attributes for the same page.
- */
-
-/* Caller's responsibility to call global_flush_tlb() for
- * performance reasons */
-#define map_page_into_agp(page) change_page_attr(page, 1, PAGE_KERNEL_NOCACHE)
-#define unmap_page_from_agp(page) change_page_attr(page, 1, PAGE_KERNEL)
-#define flush_agp_mappings() global_flush_tlb()
-
-/* Could use CLFLUSH here if the cpu supports it. But then it would
-   need to be called for each cacheline of the whole page so it may not be 
-   worth it. Would need a page for it. */
-#define flush_agp_cache() asm volatile("wbinvd":::"memory")
-
-/* Convert a physical address to an address suitable for the GART. */
-#define phys_to_gart(x) (x)
-#define gart_to_phys(x) (x)
-
-/* GATT allocation. Returns/accepts GATT kernel virtual address. */
-#define alloc_gatt_pages(order)		\
-	((char *)__get_free_pages(GFP_KERNEL, (order)))
-#define free_gatt_pages(table, order)	\
-	free_pages((unsigned long)(table), (order))
-
-#endif

include/asm-x86/alternative-asm_32.i → include/asm-x86/alternative-asm.h

+#ifdef __ASSEMBLY__
+
+#ifdef CONFIG_X86_32
+# define X86_ALIGN .long
+#else
+# define X86_ALIGN .quad
+#endif
+
 #ifdef CONFIG_SMP
 	.macro LOCK_PREFIX
 1:	lock
 	.section .smp_locks,"a"
 	.align 4
-	.long 1b
+	X86_ALIGN 1b
 	.previous
 	.endm
 #else
 	.macro LOCK_PREFIX
 	.endm
 #endif
+
+#endif  /*  __ASSEMBLY__  */

include/asm-x86/alternative-asm.i

-#ifdef CONFIG_X86_32
-# include "alternative-asm_32.i"
-#else
-# include "alternative-asm_64.i"
-#endif