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
  ...

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