Merge branch 'x86-64'

* x86-64: (83 commits)
  [PATCH] x86_64: x86_64 stack usage debugging
  [PATCH] x86_64: (resend) x86_64 stack overflow debugging
  [PATCH] x86_64: msi_apic.c build fix
  [PATCH] x86_64: i386/x86-64 Add nmi watchdog support for new Intel CPUs
  [PATCH] x86_64: Avoid broadcasting NMI IPIs
  [PATCH] x86_64: fix apic error on bootup
  [PATCH] x86_64: enlarge window for stack growth
  [PATCH] x86_64: Minor string functions optimizations
  [PATCH] x86_64: Move export symbols to their C functions
  [PATCH] x86_64: Standardize i386/x86_64 handling of NMI_VECTOR
  [PATCH] x86_64: Fix modular pc speaker
  [PATCH] x86_64: remove sys32_ni_syscall()
  [PATCH] x86_64: Do not use -ffunction-sections for modules
  [PATCH] x86_64: Add cpu_relax to apic_wait_icr_idle
  [PATCH] x86_64: adjust kstack_depth_to_print default
  [PATCH] i386/x86-64: adjust /proc/interrupts column headings
  [PATCH] x86_64: Fix race in cpu_local_* on preemptible kernels
  [PATCH] x86_64: Fix fast check in safe_smp_processor_id
  [PATCH] x86_64: x86_64 setup.c - printing cmp related boottime information
  [PATCH] i386/x86-64/ia64: Move polling flag into thread_info_status
  ...

Manual resolve of trivial conflict in arch/i386/kernel/Makefile

Documentation/x86_64/boot-options.txt

@@ -205,6 +205,27 @@ IOMMU
   pages  Prereserve that many 128K pages for the software IO bounce buffering.
   force  Force all IO through the software TLB.
 
+  calgary=[64k,128k,256k,512k,1M,2M,4M,8M]
+  calgary=[translate_empty_slots]
+  calgary=[disable=<PCI bus number>]
+
+    64k,...,8M - Set the size of each PCI slot's translation table
+    when using the Calgary IOMMU. This is the size of the translation
+    table itself in main memory. The smallest table, 64k, covers an IO
+    space of 32MB; the largest, 8MB table, can cover an IO space of
+    4GB. Normally the kernel will make the right choice by itself.
+
+    translate_empty_slots - Enable translation even on slots that have
+    no devices attached to them, in case a device will be hotplugged
+    in the future.
+
+    disable=<PCI bus number> - Disable translation on a given PHB. For
+    example, the built-in graphics adapter resides on the first bridge
+    (PCI bus number 0); if translation (isolation) is enabled on this
+    bridge, X servers that access the hardware directly from user
+    space might stop working. Use this option if you have devices that
+    are accessed from userspace directly on some PCI host bridge.
+
 Debugging
 
   oops=panic Always panic on oopses. Default is to just kill the process,

arch/i386/Kconfig

@@ -328,6 +328,15 @@ config X86_MCE_P4THERMAL
 	  Enabling this feature will cause a message to be printed when the P4
 	  enters thermal throttling.
 
+config VM86
+	default y
+	bool "Enable VM86 support" if EMBEDDED
+	help
+          This option is required by programs like DOSEMU to run 16-bit legacy
+	  code on X86 processors. It also may be needed by software like
+          XFree86 to initialize some video cards via BIOS. Disabling this
+          option saves about 6k.
+
 config TOSHIBA
 	tristate "Toshiba Laptop support"
 	---help---
@@ -1068,6 +1077,10 @@ config SCx200HR_TIMER
 	  processor goes idle (as is done by the scheduler).  The
 	  other workaround is idle=poll boot option.
 
+config K8_NB
+	def_bool y
+	depends on AGP_AMD64
+
 source "drivers/pcmcia/Kconfig"
 
 source "drivers/pci/hotplug/Kconfig"

arch/i386/boot/Makefile

@@ -109,8 +109,13 @@ fdimage288: $(BOOTIMAGE) $(obj)/mtools.conf
 isoimage: $(BOOTIMAGE)
 	-rm -rf $(obj)/isoimage
 	mkdir $(obj)/isoimage
-	cp `echo /usr/lib*/syslinux/isolinux.bin | awk '{ print $1; }'` \
-		$(obj)/isoimage
+	for i in lib lib64 share end ; do \
+		if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \
+			cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \
+			break ; \
+		fi ; \
+		if [ $$i = end ] ; then exit 1 ; fi ; \
+	done
 	cp $(BOOTIMAGE) $(obj)/isoimage/linux
 	echo '$(image_cmdline)' > $(obj)/isoimage/isolinux.cfg
 	if [ -f '$(FDINITRD)' ] ; then \

arch/i386/boot/compressed/misc.c

@@ -24,14 +24,6 @@
 
 #undef memset
 #undef memcpy
-
-/*
- * Why do we do this? Don't ask me..
- *
- * Incomprehensible are the ways of bootloaders.
- */
-static void* memset(void *, int, size_t);
-static void* memcpy(void *, __const void *, size_t);
 #define memzero(s, n)     memset ((s), 0, (n))
 
 typedef unsigned char  uch;
@@ -93,7 +85,7 @@ static unsigned char *real_mode; /* Pointer to real-mode data */
 #endif
 #define RM_SCREEN_INFO (*(struct screen_info *)(real_mode+0))
 
-extern char input_data[];
+extern unsigned char input_data[];
 extern int input_len;
 
 static long bytes_out = 0;
@@ -103,6 +95,9 @@ static unsigned long output_ptr = 0;
 static void *malloc(int size);
 static void free(void *where);
 
+static void *memset(void *s, int c, unsigned n);
+static void *memcpy(void *dest, const void *src, unsigned n);
+
 static void putstr(const char *);
 
 extern int end;
@@ -205,7 +200,7 @@ static void putstr(const char *s)
 	outb_p(0xff & (pos >> 1), vidport+1);
 }
 
-static void* memset(void* s, int c, size_t n)
+static void* memset(void* s, int c, unsigned n)
 {
 	int i;
 	char *ss = (char*)s;
@@ -214,14 +209,13 @@ static void* memset(void* s, int c, size_t n)
 	return s;
 }
 
-static void* memcpy(void* __dest, __const void* __src,
-			    size_t __n)
+static void* memcpy(void* dest, const void* src, unsigned n)
 {
 	int i;
-	char *d = (char *)__dest, *s = (char *)__src;
+	char *d = (char *)dest, *s = (char *)src;
 
-	for (i=0;i<__n;i++) d[i] = s[i];
-	return __dest;
+	for (i=0;i<n;i++) d[i] = s[i];
+	return dest;
 }
 
 /* ===========================================================================
@@ -309,7 +303,7 @@ static void setup_normal_output_buffer(void)
 #else
 	if ((RM_ALT_MEM_K > RM_EXT_MEM_K ? RM_ALT_MEM_K : RM_EXT_MEM_K) < 1024) error("Less than 2MB of memory");
 #endif
-	output_data = (char *)__PHYSICAL_START; /* Normally Points to 1M */
+	output_data = (unsigned char *)__PHYSICAL_START; /* Normally Points to 1M */
 	free_mem_end_ptr = (long)real_mode;
 }
 
@@ -324,11 +318,9 @@ static void setup_output_buffer_if_we_run_high(struct moveparams *mv)
 #ifdef STANDARD_MEMORY_BIOS_CALL
 	if (RM_EXT_MEM_K < (3*1024)) error("Less than 4MB of memory");
 #else
-	if ((RM_ALT_MEM_K > RM_EXT_MEM_K ? RM_ALT_MEM_K : RM_EXT_MEM_K) <
-			(3*1024))
-		error("Less than 4MB of memory");
+	if ((RM_ALT_MEM_K > RM_EXT_MEM_K ? RM_ALT_MEM_K : RM_EXT_MEM_K) < (3*1024)) error("Less than 4MB of memory");
 #endif	
-	mv->low_buffer_start = output_data = (char *)LOW_BUFFER_START;
+	mv->low_buffer_start = output_data = (unsigned char *)LOW_BUFFER_START;
 	low_buffer_end = ((unsigned int)real_mode > LOW_BUFFER_MAX
 	  ? LOW_BUFFER_MAX : (unsigned int)real_mode) & ~0xfff;
 	low_buffer_size = low_buffer_end - LOW_BUFFER_START;

arch/i386/kernel/Makefile

@@ -37,6 +37,7 @@ obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault.o
 obj-$(CONFIG_VM86)		+= vm86.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
+obj-$(CONFIG_K8_NB)		+= k8.o
 
 EXTRA_AFLAGS   := -traditional
 
@@ -76,3 +77,6 @@ SYSCFLAGS_vsyscall-syms.o = -r
 $(obj)/vsyscall-syms.o: $(src)/vsyscall.lds \
 			$(obj)/vsyscall-sysenter.o $(obj)/vsyscall-note.o FORCE
 	$(call if_changed,syscall)
+
+k8-y                      += ../../x86_64/kernel/k8.o
+

arch/i386/kernel/alternative.c

@@ -4,27 +4,41 @@
 #include <asm/alternative.h>
 #include <asm/sections.h>
 
-#define DEBUG 0
-#if DEBUG
-# define DPRINTK(fmt, args...) printk(fmt, args)
-#else
-# define DPRINTK(fmt, args...)
-#endif
+static int no_replacement    = 0;
+static int smp_alt_once      = 0;
+static int debug_alternative = 0;
+
+static int __init noreplacement_setup(char *s)
+{
+	no_replacement = 1;
+	return 1;
+}
+static int __init bootonly(char *str)
+{
+	smp_alt_once = 1;
+	return 1;
+}
+static int __init debug_alt(char *str)
+{
+	debug_alternative = 1;
+	return 1;
+}
 
+__setup("noreplacement", noreplacement_setup);
+__setup("smp-alt-boot", bootonly);
+__setup("debug-alternative", debug_alt);
+
+#define DPRINTK(fmt, args...) if (debug_alternative) \
+	printk(KERN_DEBUG fmt, args)
+
+#ifdef GENERIC_NOP1
 /* 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: "
 	GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
 	GENERIC_NOP7 GENERIC_NOP8);
-asm("\t.data\nk8nops: "
-	K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
-	K8_NOP7 K8_NOP8);
-asm("\t.data\nk7nops: "
-	K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
-	K7_NOP7 K7_NOP8);
-
-extern unsigned char intelnops[], k8nops[], k7nops[];
+extern unsigned char intelnops[];
 static unsigned char *intel_nops[ASM_NOP_MAX+1] = {
 	NULL,
 	intelnops,
@@ -36,6 +50,13 @@ static unsigned char *intel_nops[ASM_NOP_MAX+1] = {
 	intelnops + 1 + 2 + 3 + 4 + 5 + 6,
 	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
 };
+#endif
+
+#ifdef K8_NOP1
+asm("\t.data\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] = {
 	NULL,
 	k8nops,
@@ -47,6 +68,13 @@ static unsigned char *k8_nops[ASM_NOP_MAX+1] = {
 	k8nops + 1 + 2 + 3 + 4 + 5 + 6,
 	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
 };
+#endif
+
+#ifdef K7_NOP1
+asm("\t.data\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] = {
 	NULL,
 	k7nops,
@@ -58,6 +86,18 @@ static unsigned char *k7_nops[ASM_NOP_MAX+1] = {
 	k7nops + 1 + 2 + 3 + 4 + 5 + 6,
 	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
 };
+#endif
+
+#ifdef CONFIG_X86_64
+
+extern char __vsyscall_0;
+static inline unsigned char** find_nop_table(void)
+{
+	return k8_nops;
+}
+
+#else /* CONFIG_X86_64 */
+
 static struct nop {
 	int cpuid;
 	unsigned char **noptable;
@@ -67,14 +107,6 @@ static struct nop {
 	{ -1, NULL }
 };
 
-
-extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
-extern struct alt_instr __smp_alt_instructions[], __smp_alt_instructions_end[];
-extern u8 *__smp_locks[], *__smp_locks_end[];
-
-extern u8 __smp_alt_begin[], __smp_alt_end[];
-
-
 static unsigned char** find_nop_table(void)
 {
 	unsigned char **noptable = intel_nops;
@@ -89,6 +121,14 @@ static unsigned char** find_nop_table(void)
 	return noptable;
 }
 
+#endif /* CONFIG_X86_64 */
+
+extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+extern struct alt_instr __smp_alt_instructions[], __smp_alt_instructions_end[];
+extern u8 *__smp_locks[], *__smp_locks_end[];
+
+extern u8 __smp_alt_begin[], __smp_alt_end[];
+
 /* Replace instructions with better alternatives for this CPU type.
    This runs before SMP is initialized to avoid SMP problems with
    self modifying code. This implies that assymetric systems where
@@ -99,6 +139,7 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 	unsigned char **noptable = find_nop_table();
 	struct alt_instr *a;
+	u8 *instr;
 	int diff, i, k;
 
 	DPRINTK("%s: alt table %p -> %p\n", __FUNCTION__, start, end);
@@ -106,7 +147,16 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 		BUG_ON(a->replacementlen > a->instrlen);
 		if (!boot_cpu_has(a->cpuid))
 			continue;
-		memcpy(a->instr, a->replacement, a->replacementlen);
+		instr = a->instr;
+#ifdef CONFIG_X86_64
+		/* vsyscall code is not mapped yet. resolve it manually. */
+		if (instr >= (u8 *)VSYSCALL_START && instr < (u8*)VSYSCALL_END) {
+			instr = __va(instr - (u8*)VSYSCALL_START + (u8*)__pa_symbol(&__vsyscall_0));
+			DPRINTK("%s: vsyscall fixup: %p => %p\n",
+				__FUNCTION__, a->instr, instr);
+		}
+#endif
+		memcpy(instr, a->replacement, a->replacementlen);
 		diff = a->instrlen - a->replacementlen;
 		/* Pad the rest with nops */
 		for (i = a->replacementlen; diff > 0; diff -= k, i += k) {
@@ -186,14 +236,6 @@ struct smp_alt_module {
 static LIST_HEAD(smp_alt_modules);
 static DEFINE_SPINLOCK(smp_alt);
 
-static int smp_alt_once = 0;
-static int __init bootonly(char *str)
-{
-	smp_alt_once = 1;
-	return 1;
-}
-__setup("smp-alt-boot", bootonly);
-
 void alternatives_smp_module_add(struct module *mod, char *name,
 				 void *locks, void *locks_end,
 				 void *text,  void *text_end)
@@ -201,6 +243,9 @@ void alternatives_smp_module_add(struct module *mod, char *name,
 	struct smp_alt_module *smp;
 	unsigned long flags;
 
+	if (no_replacement)
+		return;
+
 	if (smp_alt_once) {
 		if (boot_cpu_has(X86_FEATURE_UP))
 			alternatives_smp_unlock(locks, locks_end,
@@ -235,7 +280,7 @@ void alternatives_smp_module_del(struct module *mod)
 	struct smp_alt_module *item;
 	unsigned long flags;
 
-	if (smp_alt_once)
+	if (no_replacement || smp_alt_once)
 		return;
 
 	spin_lock_irqsave(&smp_alt, flags);
@@ -256,7 +301,7 @@ void alternatives_smp_switch(int smp)
 	struct smp_alt_module *mod;
 	unsigned long flags;
 
-	if (smp_alt_once)
+	if (no_replacement || smp_alt_once)
 		return;
 	BUG_ON(!smp && (num_online_cpus() > 1));
 
@@ -285,6 +330,13 @@ void alternatives_smp_switch(int smp)
 
 void __init alternative_instructions(void)
 {
+	if (no_replacement) {
+		printk(KERN_INFO "(SMP-)alternatives turned off\n");
+		free_init_pages("SMP alternatives",
+				(unsigned long)__smp_alt_begin,
+				(unsigned long)__smp_alt_end);
+		return;
+	}
 	apply_alternatives(__alt_instructions, __alt_instructions_end);
 
 	/* switch to patch-once-at-boottime-only mode and free the

arch/i386/kernel/apic.c

@@ -36,6 +36,7 @@
 #include <asm/arch_hooks.h>
 #include <asm/hpet.h>
 #include <asm/i8253.h>
+#include <asm/nmi.h>
 
 #include <mach_apic.h>
 #include <mach_apicdef.h>
@@ -156,7 +157,7 @@ void clear_local_APIC(void)
 	maxlvt = get_maxlvt();
 
 	/*
-	 * Masking an LVT entry on a P6 can trigger a local APIC error
+	 * Masking an LVT entry can trigger a local APIC error
 	 * if the vector is zero. Mask LVTERR first to prevent this.
 	 */
 	if (maxlvt >= 3) {
@@ -1117,7 +1118,18 @@ void disable_APIC_timer(void)
 		unsigned long v;
 
 		v = apic_read(APIC_LVTT);
-		apic_write_around(APIC_LVTT, v | APIC_LVT_MASKED);
+		/*
+		 * When an illegal vector value (0-15) is written to an LVT
+		 * entry and delivery mode is Fixed, the APIC may signal an
+		 * illegal vector error, with out regard to whether the mask
+		 * bit is set or whether an interrupt is actually seen on input.
+		 *
+		 * Boot sequence might call this function when the LVTT has
+		 * '0' vector value. So make sure vector field is set to
+		 * valid value.
+		 */
+		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+		apic_write_around(APIC_LVTT, v);
 	}
 }
 

arch/i386/kernel/apm.c

@@ -764,9 +764,9 @@ static int apm_do_idle(void)
 	int	idled = 0;
 	int	polling;
 
-	polling = test_thread_flag(TIF_POLLING_NRFLAG);
+	polling = !!(current_thread_info()->status & TS_POLLING);
 	if (polling) {
-		clear_thread_flag(TIF_POLLING_NRFLAG);
+		current_thread_info()->status &= ~TS_POLLING;
 		smp_mb__after_clear_bit();
 	}
 	if (!need_resched()) {
@@ -774,7 +774,7 @@ static int apm_do_idle(void)
 		ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax);
 	}
 	if (polling)
-		set_thread_flag(TIF_POLLING_NRFLAG);
+		current_thread_info()->status |= TS_POLLING;
 
 	if (!idled)
 		return 0;

arch/i386/kernel/cpu/amd.c

@@ -224,15 +224,17 @@ static void __init init_amd(struct cpuinfo_x86 *c)
 
 #ifdef CONFIG_X86_HT
 	/*
-	 * On a AMD dual core setup the lower bits of the APIC id
-	 * distingush the cores.  Assumes number of cores is a power
-	 * of two.
+	 * On a AMD multi core setup the lower bits of the APIC id
+	 * distingush the cores.
 	 */
 	if (c->x86_max_cores > 1) {
 		int cpu = smp_processor_id();
-		unsigned bits = 0;
-		while ((1 << bits) < c->x86_max_cores)
-			bits++;
+		unsigned bits = (cpuid_ecx(0x80000008) >> 12) & 0xf;
+
+		if (bits == 0) {
+			while ((1 << bits) < c->x86_max_cores)
+				bits++;
+		}
 		cpu_core_id[cpu] = phys_proc_id[cpu] & ((1<<bits)-1);
 		phys_proc_id[cpu] >>= bits;
 		printk(KERN_INFO "CPU %d(%d) -> Core %d\n",
@@ -240,6 +242,8 @@ static void __init init_amd(struct cpuinfo_x86 *c)
 	}
 #endif
 
+	if (cpuid_eax(0x80000000) >= 0x80000006)
+		num_cache_leaves = 3;
 }
 
 static unsigned int amd_size_cache(struct cpuinfo_x86 * c, unsigned int size)

arch/i386/kernel/cpu/intel.c

@@ -122,6 +122,12 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 
 	select_idle_routine(c);
 	l2 = init_intel_cacheinfo(c);
+	if (c->cpuid_level > 9 ) {
+		unsigned eax = cpuid_eax(10);
+		/* Check for version and the number of counters */
+		if ((eax & 0xff) && (((eax>>8) & 0xff) > 1))
+			set_bit(X86_FEATURE_ARCH_PERFMON, c->x86_capability);
+	}
 
 	/* SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until model 3 mask 3 */
 	if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633)

arch/i386/kernel/cpu/intel_cacheinfo.c

@@ -4,6 +4,7 @@
  *      Changes:
  *      Venkatesh Pallipadi	: Adding cache identification through cpuid(4)
  *		Ashok Raj <ashok.raj@intel.com>: Work with CPU hotplug infrastructure.
+ *	Andi Kleen		: CPUID4 emulation on AMD.
  */
 
 #include <linux/init.h>
@@ -130,25 +131,111 @@ struct _cpuid4_info {
 	cpumask_t shared_cpu_map;
 };
 
-static unsigned short			num_cache_leaves;
+unsigned short			num_cache_leaves;
+
+/* AMD doesn't have CPUID4. Emulate it here to report the same
+   information to the user.  This makes some assumptions about the machine:
+   No L3, L2 not shared, no SMT etc. that is currently true on AMD CPUs.
+
+   In theory the TLBs could be reported as fake type (they are in "dummy").
+   Maybe later */
+union l1_cache {
+	struct {
+		unsigned line_size : 8;
+		unsigned lines_per_tag : 8;
+		unsigned assoc : 8;
+		unsigned size_in_kb : 8;
+	};
+	unsigned val;
+};
+
+union l2_cache {
+	struct {
+		unsigned line_size : 8;
+		unsigned lines_per_tag : 4;
+		unsigned assoc : 4;
+		unsigned size_in_kb : 16;
+	};
+	unsigned val;
+};
+
+static unsigned short assocs[] = {
+	[1] = 1, [2] = 2, [4] = 4, [6] = 8,
+	[8] = 16,
+	[0xf] = 0xffff // ??
+	};
+static unsigned char levels[] = { 1, 1, 2 };
+static unsigned char types[] = { 1, 2, 3 };
+
+static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
+		       union _cpuid4_leaf_ebx *ebx,
+		       union _cpuid4_leaf_ecx *ecx)
+{
+	unsigned dummy;
+	unsigned line_size, lines_per_tag, assoc, size_in_kb;
+	union l1_cache l1i, l1d;
+	union l2_cache l2;
+
+	eax->full = 0;
+	ebx->full = 0;
+	ecx->full = 0;
+
+	cpuid(0x80000005, &dummy, &dummy, &l1d.val, &l1i.val);
+	cpuid(0x80000006, &dummy, &dummy, &l2.val, &dummy);
+
+	if (leaf > 2 || !l1d.val || !l1i.val || !l2.val)
+		return;
+
+	eax->split.is_self_initializing = 1;
+	eax->split.type = types[leaf];
+	eax->split.level = levels[leaf];
+	eax->split.num_threads_sharing = 0;
+	eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
+
+	if (leaf <= 1) {
+		union l1_cache *l1 = leaf == 0 ? &l1d : &l1i;
+		assoc = l1->assoc;
+		line_size = l1->line_size;
+		lines_per_tag = l1->lines_per_tag;
+		size_in_kb = l1->size_in_kb;
+	} else {
+		assoc = l2.assoc;
+		line_size = l2.line_size;
+		lines_per_tag = l2.lines_per_tag;
+		/* cpu_data has errata corrections for K7 applied */
+		size_in_kb = current_cpu_data.x86_cache_size;
+	}
+
+	if (assoc == 0xf)
+		eax->split.is_fully_associative = 1;
+	ebx->split.coherency_line_size = line_size - 1;
+	ebx->split.ways_of_associativity = assocs[assoc] - 1;
+	ebx->split.physical_line_partition = lines_per_tag - 1;
+	ecx->split.number_of_sets = (size_in_kb * 1024) / line_size /
+		(ebx->split.ways_of_associativity + 1) - 1;
+}
 
 static int __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
 {
-	unsigned int		eax, ebx, ecx, edx;
-	union _cpuid4_leaf_eax	cache_eax;
+	union _cpuid4_leaf_eax 	eax;
+	union _cpuid4_leaf_ebx 	ebx;
+	union _cpuid4_leaf_ecx 	ecx;
+	unsigned		edx;
 
-	cpuid_count(4, index, &eax, &ebx, &ecx, &edx);
-	cache_eax.full = eax;
-	if (cache_eax.split.type == CACHE_TYPE_NULL)
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		amd_cpuid4(index, &eax, &ebx, &ecx);
+	else
+		cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full,  &edx);
+	if (eax.split.type == CACHE_TYPE_NULL)
 		return -EIO; /* better error ? */
 
-	this_leaf->eax.full = eax;
-	this_leaf->ebx.full = ebx;
-	this_leaf->ecx.full = ecx;
-	this_leaf->size = (this_leaf->ecx.split.number_of_sets + 1) *
-		(this_leaf->ebx.split.coherency_line_size + 1) *
-		(this_leaf->ebx.split.physical_line_partition + 1) *
-		(this_leaf->ebx.split.ways_of_associativity + 1);
+	this_leaf->eax = eax;
+	this_leaf->ebx = ebx;
+	this_leaf->ecx = ecx;
+	this_leaf->size = (ecx.split.number_of_sets + 1) *
+		(ebx.split.coherency_line_size + 1) *
+		(ebx.split.physical_line_partition + 1) *
+		(ebx.split.ways_of_associativity + 1);
 	return 0;
 }
 

arch/i386/kernel/crash.c

@@ -120,14 +120,9 @@ static int crash_nmi_callback(struct pt_regs *regs, int cpu)
 	return 1;
 }
 
-/*
- * By using the NMI code instead of a vector we just sneak thru the
- * word generator coming out with just what we want.  AND it does
- * not matter if clustered_apic_mode is set or not.
- */
 static void smp_send_nmi_allbutself(void)
 {
-	send_IPI_allbutself(APIC_DM_NMI);
+	send_IPI_allbutself(NMI_VECTOR);
 }
 
 static void nmi_shootdown_cpus(void)

arch/i386/kernel/io_apic.c

@@ -38,6 +38,7 @@
 #include <asm/desc.h>
 #include <asm/timer.h>
 #include <asm/i8259.h>
+#include <asm/nmi.h>
 
 #include <mach_apic.h>
 
@@ -50,6 +51,7 @@ atomic_t irq_mis_count;
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 
 static DEFINE_SPINLOCK(ioapic_lock);
+static DEFINE_SPINLOCK(vector_lock);
 
 int timer_over_8254 __initdata = 1;
 
@@ -1161,10 +1163,17 @@ u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 };
 int assign_irq_vector(int irq)
 {
 	static int current_vector = FIRST_DEVICE_VECTOR, offset = 0;
+	unsigned long flags;
+	int vector;
+
+	BUG_ON(irq != AUTO_ASSIGN && (unsigned)irq >= NR_IRQ_VECTORS);
 
-	BUG_ON(irq >= NR_IRQ_VECTORS);
-	if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0)
+	spin_lock_irqsave(&vector_lock, flags);
+
+	if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0) {
+		spin_unlock_irqrestore(&vector_lock, flags);
 		return IO_APIC_VECTOR(irq);
+	}
 next:
 	current_vector += 8;
 	if (current_vector == SYSCALL_VECTOR)
@@ -1172,16 +1181,21 @@ int assign_irq_vector(int irq)
 
 	if (current_vector >= FIRST_SYSTEM_VECTOR) {
 		offset++;
-		if (!(offset%8))
+		if (!(offset%8)) {
+			spin_unlock_irqrestore(&vector_lock, flags);
 			return -ENOSPC;
+		}
 		current_vector = FIRST_DEVICE_VECTOR + offset;
 	}
 
-	vector_irq[current_vector] = irq;
+	vector = current_vector;
+	vector_irq[vector] = irq;
 	if (irq != AUTO_ASSIGN)
-		IO_APIC_VECTOR(irq) = current_vector;
+		IO_APIC_VECTOR(irq) = vector;
 
-	return current_vector;
+	spin_unlock_irqrestore(&vector_lock, flags);
+
+	return vector;
 }
 
 static struct hw_interrupt_type ioapic_level_type;
@@ -1193,21 +1207,14 @@ static struct hw_interrupt_type ioapic_edge_type;
 
 static inline void ioapic_register_intr(int irq, int vector, unsigned long trigger)
 {
-	if (use_pci_vector() && !platform_legacy_irq(irq)) {
-		if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
-				trigger == IOAPIC_LEVEL)
-			irq_desc[vector].handler = &ioapic_level_type;
-		else
-			irq_desc[vector].handler = &ioapic_edge_type;
-		set_intr_gate(vector, interrupt[vector]);
-	} else	{
-		if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
-				trigger == IOAPIC_LEVEL)
-			irq_desc[irq].handler = &ioapic_level_type;
-		else
-			irq_desc[irq].handler = &ioapic_edge_type;
-		set_intr_gate(vector, interrupt[irq]);
-	}
+	unsigned idx = use_pci_vector() && !platform_legacy_irq(irq) ? vector : irq;
+
+	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
+			trigger == IOAPIC_LEVEL)
+		irq_desc[idx].handler = &ioapic_level_type;
+	else
+		irq_desc[idx].handler = &ioapic_edge_type;
+	set_intr_gate(vector, interrupt[idx]);
 }
 
 static void __init setup_IO_APIC_irqs(void)

arch/i386/kernel/irq.c

@@ -227,7 +227,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (i == 0) {
 		seq_printf(p, "           ");
 		for_each_online_cpu(j)
-			seq_printf(p, "CPU%d       ",j);
+			seq_printf(p, "CPU%-8d",j);
 		seq_putc(p, '\n');
 	}
 

arch/i386/kernel/nmi.c

@@ -14,21 +14,17 @@
  */
 
 #include <linux/config.h>
-#include <linux/mm.h>
 #include <linux/delay.h>
-#include <linux/bootmem.h>
-#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
-#include <linux/mc146818rtc.h>
-#include <linux/kernel_stat.h>
 #include <linux/module.h>
 #include <linux/nmi.h>
 #include <linux/sysdev.h>
 #include <linux/sysctl.h>
+#include <linux/percpu.h>
 
 #include <asm/smp.h>
-#include <asm/div64.h>
 #include <asm/nmi.h>
+#include <asm/intel_arch_perfmon.h>
 
 #include "mach_traps.h"
 
@@ -100,6 +96,9 @@ int nmi_active;
 	(P4_CCCR_OVF_PMI0|P4_CCCR_THRESHOLD(15)|P4_CCCR_COMPLEMENT|	\
 	 P4_CCCR_COMPARE|P4_CCCR_REQUIRED|P4_CCCR_ESCR_SELECT(4)|P4_CCCR_ENABLE)
 
+#define ARCH_PERFMON_NMI_EVENT_SEL	ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
+#define ARCH_PERFMON_NMI_EVENT_UMASK	ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
+
 #ifdef CONFIG_SMP
 /* The performance counters used by NMI_LOCAL_APIC don't trigger when
  * the CPU is idle. To make sure the NMI watchdog really ticks on all
@@ -212,6 +211,8 @@ static int __init setup_nmi_watchdog(char *str)
 
 __setup("nmi_watchdog=", setup_nmi_watchdog);
 
+static void disable_intel_arch_watchdog(void);
+
 static void disable_lapic_nmi_watchdog(void)
 {
 	if (nmi_active <= 0)
@@ -221,6 +222,10 @@ static void disable_lapic_nmi_watchdog(void)
 		wrmsr(MSR_K7_EVNTSEL0, 0, 0);
 		break;
 	case X86_VENDOR_INTEL:
+		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
+			disable_intel_arch_watchdog();
+			break;
+		}
 		switch (boot_cpu_data.x86) {
 		case 6:
 			if (boot_cpu_data.x86_model > 0xd)
@@ -449,6 +454,53 @@ static int setup_p4_watchdog(void)
 	return 1;
 }
 
+static void disable_intel_arch_watchdog(void)
+{
+	unsigned ebx;
+
+	/*
+	 * Check whether the Architectural PerfMon supports
+	 * Unhalted Core Cycles Event or not.
+	 * NOTE: Corresponding bit = 0 in ebp indicates event present.
+	 */
+	ebx = cpuid_ebx(10);
+	if (!(ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
+		wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, 0, 0);
+}
+
+static int setup_intel_arch_watchdog(void)
+{
+	unsigned int evntsel;
+	unsigned ebx;
+
+	/*
+	 * Check whether the Architectural PerfMon supports
+	 * Unhalted Core Cycles Event or not.
+	 * NOTE: Corresponding bit = 0 in ebp indicates event present.
+	 */
+	ebx = cpuid_ebx(10);
+	if ((ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
+		return 0;
+
+	nmi_perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0;
+
+	clear_msr_range(MSR_ARCH_PERFMON_EVENTSEL0, 2);
+	clear_msr_range(MSR_ARCH_PERFMON_PERFCTR0, 2);
+
+	evntsel = ARCH_PERFMON_EVENTSEL_INT
+		| ARCH_PERFMON_EVENTSEL_OS
+		| ARCH_PERFMON_EVENTSEL_USR
+		| ARCH_PERFMON_NMI_EVENT_SEL
+		| ARCH_PERFMON_NMI_EVENT_UMASK;
+
+	wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, evntsel, 0);
+	write_watchdog_counter("INTEL_ARCH_PERFCTR0");
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+	wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, evntsel, 0);
+	return 1;
+}
+
 void setup_apic_nmi_watchdog (void)
 {
 	switch (boot_cpu_data.x86_vendor) {
@@ -458,6 +510,11 @@ void setup_apic_nmi_watchdog (void)
 		setup_k7_watchdog();
 		break;
 	case X86_VENDOR_INTEL:
+		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
+			if (!setup_intel_arch_watchdog())
+				return;
+			break;
+		}
 		switch (boot_cpu_data.x86) {
 		case 6:
 			if (boot_cpu_data.x86_model > 0xd)
@@ -561,7 +618,8 @@ void nmi_watchdog_tick (struct pt_regs * regs)
 			wrmsr(MSR_P4_IQ_CCCR0, nmi_p4_cccr_val, 0);
 			apic_write(APIC_LVTPC, APIC_DM_NMI);
 		}
-		else if (nmi_perfctr_msr == MSR_P6_PERFCTR0) {
+		else if (nmi_perfctr_msr == MSR_P6_PERFCTR0 ||
+		         nmi_perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
 			/* Only P6 based Pentium M need to re-unmask
 			 * the apic vector but it doesn't hurt
 			 * other P6 variant */

arch/i386/kernel/process.c

@@ -102,7 +102,7 @@ void default_idle(void)
 	local_irq_enable();
 
 	if (!hlt_counter && boot_cpu_data.hlt_works_ok) {
-		clear_thread_flag(TIF_POLLING_NRFLAG);
+		current_thread_info()->status &= ~TS_POLLING;
 		smp_mb__after_clear_bit();
 		while (!need_resched()) {
 			local_irq_disable();
@@ -111,7 +111,7 @@ void default_idle(void)
 			else
 				local_irq_enable();
 		}
-		set_thread_flag(TIF_POLLING_NRFLAG);
+		current_thread_info()->status |= TS_POLLING;
 	} else {
 		while (!need_resched())
 			cpu_relax();
@@ -174,7 +174,7 @@ void cpu_idle(void)
 {
 	int cpu = smp_processor_id();
 
-	set_thread_flag(TIF_POLLING_NRFLAG);
+	current_thread_info()->status |= TS_POLLING;
 
 	/* endless idle loop with no priority at all */
 	while (1) {
@@ -312,7 +312,7 @@ void show_regs(struct pt_regs * regs)
 	cr3 = read_cr3();
 	cr4 = read_cr4_safe();
 	printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4);
-	show_trace(NULL, &regs->esp);
+	show_trace(NULL, regs, &regs->esp);
 }
 
 /*

arch/i386/kernel/smp.c

@@ -114,7 +114,17 @@ DEFINE_PER_CPU(struct tlb_state, cpu_tlbstate) ____cacheline_aligned = { &init_m
 
 static inline int __prepare_ICR (unsigned int shortcut, int vector)
 {
-	return APIC_DM_FIXED | shortcut | vector | APIC_DEST_LOGICAL;
+	unsigned int icr = shortcut | APIC_DEST_LOGICAL;
+
+	switch (vector) {
+	default:
+		icr |= APIC_DM_FIXED | vector;
+		break;
+	case NMI_VECTOR:
+		icr |= APIC_DM_NMI;
+		break;
+	}
+	return icr;
 }
 
 static inline int __prepare_ICR2 (unsigned int mask)

arch/i386/kernel/smpboot.c

@@ -52,6 +52,7 @@
 #include <asm/tlbflush.h>
 #include <asm/desc.h>
 #include <asm/arch_hooks.h>
+#include <asm/nmi.h>
 
 #include <mach_apic.h>
 #include <mach_wakecpu.h>

arch/i386/kernel/traps.c

@@ -28,6 +28,7 @@
 #include <linux/utsname.h>
 #include <linux/kprobes.h>
 #include <linux/kexec.h>
+#include <linux/unwind.h>
 
 #ifdef CONFIG_EISA
 #include <linux/ioport.h>
@@ -47,7 +48,7 @@
 #include <asm/desc.h>
 #include <asm/i387.h>
 #include <asm/nmi.h>
-
+#include <asm/unwind.h>
 #include <asm/smp.h>
 #include <asm/arch_hooks.h>
 #include <asm/kdebug.h>
@@ -92,6 +93,7 @@ asmlinkage void spurious_interrupt_bug(void);
 asmlinkage void machine_check(void);
 
 static int kstack_depth_to_print = 24;
+static int call_trace = 1;
 ATOMIC_NOTIFIER_HEAD(i386die_chain);
 
 int register_die_notifier(struct notifier_block *nb)
@@ -170,7 +172,23 @@ static inline unsigned long print_context_stack(struct thread_info *tinfo,
 	return ebp;
 }
 
-static void show_trace_log_lvl(struct task_struct *task,
+static asmlinkage int show_trace_unwind(struct unwind_frame_info *info, void *log_lvl)
+{
+	int n = 0;
+	int printed = 0; /* nr of entries already printed on current line */
+
+	while (unwind(info) == 0 && UNW_PC(info)) {
+		++n;
+		printed = print_addr_and_symbol(UNW_PC(info), log_lvl, printed);
+		if (arch_unw_user_mode(info))
+			break;
+	}
+	if (printed)
+		printk("\n");
+	return n;
+}
+
+static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			       unsigned long *stack, char *log_lvl)
 {
 	unsigned long ebp;
@@ -178,6 +196,26 @@ static void show_trace_log_lvl(struct task_struct *task,
 	if (!task)
 		task = current;
 
+	if (call_trace >= 0) {
+		int unw_ret = 0;
+		struct unwind_frame_info info;
+
+		if (regs) {
+			if (unwind_init_frame_info(&info, task, regs) == 0)
+				unw_ret = show_trace_unwind(&info, log_lvl);
+		} else if (task == current)
+			unw_ret = unwind_init_running(&info, show_trace_unwind, log_lvl);
+		else {
+			if (unwind_init_blocked(&info, task) == 0)
+				unw_ret = show_trace_unwind(&info, log_lvl);
+		}
+		if (unw_ret > 0) {
+			if (call_trace > 0)
+				return;
+			printk("%sLegacy call trace:\n", log_lvl);
+		}
+	}
+
 	if (task == current) {
 		/* Grab ebp right from our regs */
 		asm ("movl %%ebp, %0" : "=r" (ebp) : );
@@ -198,13 +236,13 @@ static void show_trace_log_lvl(struct task_struct *task,
 	}
 }
 
-void show_trace(struct task_struct *task, unsigned long * stack)
+void show_trace(struct task_struct *task, struct pt_regs *regs, unsigned long * stack)
 {
-	show_trace_log_lvl(task, stack, "");
+	show_trace_log_lvl(task, regs, stack, "");
 }
 
-static void show_stack_log_lvl(struct task_struct *task, unsigned long *esp,
-			       char *log_lvl)
+static void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+			       unsigned long *esp, char *log_lvl)
 {
 	unsigned long *stack;
 	int i;
@@ -225,13 +263,13 @@ static void show_stack_log_lvl(struct task_struct *task, unsigned long *esp,
 		printk("%08lx ", *stack++);
 	}
 	printk("\n%sCall Trace:\n", log_lvl);
-	show_trace_log_lvl(task, esp, log_lvl);
+	show_trace_log_lvl(task, regs, esp, log_lvl);
 }
 
 void show_stack(struct task_struct *task, unsigned long *esp)
 {
 	printk("       ");
-	show_stack_log_lvl(task, esp, "");
+	show_stack_log_lvl(task, NULL, esp, "");
 }
 
 /*
@@ -241,7 +279,7 @@ void dump_stack(void)
 {
 	unsigned long stack;
 
-	show_trace(current, &stack);
+	show_trace(current, NULL, &stack);
 }
 
 EXPORT_SYMBOL(dump_stack);
@@ -285,7 +323,7 @@ void show_registers(struct pt_regs *regs)
 		u8 __user *eip;
 
 		printk("\n" KERN_EMERG "Stack: ");
-		show_stack_log_lvl(NULL, (unsigned long *)esp, KERN_EMERG);
+		show_stack_log_lvl(NULL, regs, (unsigned long *)esp, KERN_EMERG);
 
 		printk(KERN_EMERG "Code: ");
 
@@ -1215,3 +1253,15 @@ static int __init kstack_setup(char *s)
 	return 1;
 }
 __setup("kstack=", kstack_setup);
+
+static int __init call_trace_setup(char *s)
+{
+	if (strcmp(s, "old") == 0)
+		call_trace = -1;
+	else if (strcmp(s, "both") == 0)
+		call_trace = 0;
+	else if (strcmp(s, "new") == 0)
+		call_trace = 1;
+	return 1;
+}
+__setup("call_trace=", call_trace_setup);

arch/i386/kernel/vmlinux.lds.S

@@ -71,6 +71,15 @@ SECTIONS
   .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) { *(.data.read_mostly) }
   _edata = .;			/* End of data section */
 
+#ifdef CONFIG_STACK_UNWIND
+  . = ALIGN(4);
+  .eh_frame : AT(ADDR(.eh_frame) - LOAD_OFFSET) {
+	__start_unwind = .;
+  	*(.eh_frame)
+	__end_unwind = .;
+  }
+#endif
+
   . = ALIGN(THREAD_SIZE);	/* init_task */
   .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
 	*(.data.init_task)

arch/i386/oprofile/op_model_athlon.c

@@ -13,6 +13,7 @@
 #include <linux/oprofile.h>
 #include <asm/ptrace.h>
 #include <asm/msr.h>
+#include <asm/nmi.h>
  
 #include "op_x86_model.h"
 #include "op_counter.h"

arch/i386/oprofile/op_model_p4.c

@@ -14,6 +14,7 @@
 #include <asm/ptrace.h>
 #include <asm/fixmap.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 #include "op_x86_model.h"
 #include "op_counter.h"

arch/i386/oprofile/op_model_ppro.c

@@ -14,6 +14,7 @@
 #include <asm/ptrace.h>
 #include <asm/msr.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
  
 #include "op_x86_model.h"
 #include "op_counter.h"

arch/ia64/kernel/process.c

@@ -272,9 +272,9 @@ cpu_idle (void)
 	/* endless idle loop with no priority at all */
 	while (1) {
 		if (can_do_pal_halt)
-			clear_thread_flag(TIF_POLLING_NRFLAG);
+			current_thread_info()->status &= ~TS_POLLING;
 		else
-			set_thread_flag(TIF_POLLING_NRFLAG);
+			current_thread_info()->status |= TS_POLLING;
 
 		if (!need_resched()) {
 			void (*idle)(void);

arch/x86_64/Kconfig

@@ -386,24 +386,45 @@ config HPET_EMULATE_RTC
 	bool "Provide RTC interrupt"
 	depends on HPET_TIMER && RTC=y
 
-config GART_IOMMU
-	bool "K8 GART IOMMU support"
+# Mark as embedded because too many people got it wrong.
+# The code disables itself when not needed.
+config IOMMU
+	bool "IOMMU support" if EMBEDDED
 	default y
 	select SWIOTLB
 	select AGP
 	depends on PCI
 	help
-	  Support for hardware IOMMU in AMD's Opteron/Athlon64 Processors
-	  and for the bounce buffering software IOMMU.
-	  Needed to run systems with more than 3GB of memory properly with
-	  32-bit PCI devices that do not support DAC (Double Address Cycle).
-	  The IOMMU can be turned off at runtime with the iommu=off parameter.
-  	  Normally the kernel will take the right choice by itself.
-  	  This option includes a driver for the AMD Opteron/Athlon64 IOMMU
-  	  northbridge and a software emulation used on other systems without
-	  hardware IOMMU.  If unsure, say Y.
-
-# need this always selected by GART_IOMMU for the VIA workaround
+	  Support for full DMA access of devices with 32bit memory access only
+	  on systems with more than 3GB. This is usually needed for USB,
+	  sound, many IDE/SATA chipsets and some other devices.
+	  Provides a driver for the AMD Athlon64/Opteron/Turion/Sempron GART
+	  based IOMMU and a software bounce buffer based IOMMU used on Intel
+	  systems and as fallback.
+	  The code is only active when needed (enough memory and limited
+	  device) unless CONFIG_IOMMU_DEBUG or iommu=force is specified
+	  too.
+
+config CALGARY_IOMMU
+	bool "IBM Calgary IOMMU support"
+	default y
+	select SWIOTLB
+	depends on PCI && EXPERIMENTAL
+	help
+	  Support for hardware IOMMUs in IBM's xSeries x366 and x460
+	  systems. Needed to run systems with more than 3GB of memory
+	  properly with 32-bit PCI devices that do not support DAC
+	  (Double Address Cycle). Calgary also supports bus level
+	  isolation, where all DMAs pass through the IOMMU.  This
+	  prevents them from going anywhere except their intended
+	  destination. This catches hard-to-find kernel bugs and
+	  mis-behaving drivers and devices that do not use the DMA-API
+	  properly to set up their DMA buffers.  The IOMMU can be
+	  turned off at boot time with the iommu=off parameter.
+	  Normally the kernel will make the right choice by itself.
+	  If unsure, say Y.
+
+# need this always selected by IOMMU for the VIA workaround
 config SWIOTLB
 	bool
 
@@ -501,6 +522,10 @@ config REORDER
          optimal TLB usage. If you have pretty much any version of binutils, 
 	 this can increase your kernel build time by roughly one minute.
 
+config K8_NB
+	def_bool y
+	depends on AGP_AMD64 || IOMMU || (PCI && NUMA)
+
 endmenu
 
 #

arch/x86_64/Kconfig.debug

@@ -13,7 +13,7 @@ config DEBUG_RODATA
 	 If in doubt, say "N".
 
 config IOMMU_DEBUG
-       depends on GART_IOMMU && DEBUG_KERNEL
+       depends on IOMMU && DEBUG_KERNEL
        bool "Enable IOMMU debugging"
        help
          Force the IOMMU to on even when you have less than 4GB of
@@ -35,6 +35,22 @@ config IOMMU_LEAK
          Add a simple leak tracer to the IOMMU code. This is useful when you
 	 are debugging a buggy device driver that leaks IOMMU mappings.
 
+config DEBUG_STACKOVERFLOW
+        bool "Check for stack overflows"
+        depends on DEBUG_KERNEL
+        help
+	  This option will cause messages to be printed if free stack space
+	  drops below a certain limit.
+
+config DEBUG_STACK_USAGE
+        bool "Stack utilization instrumentation"
+        depends on DEBUG_KERNEL
+        help
+	  Enables the display of the minimum amount of free stack which each
+	  task has ever had available in the sysrq-T and sysrq-P debug output.
+
+	  This option will slow down process creation somewhat.
+
 #config X86_REMOTE_DEBUG
 #       bool "kgdb debugging stub"
 

arch/x86_64/Makefile

@@ -27,6 +27,7 @@ LDFLAGS_vmlinux :=
 CHECKFLAGS      += -D__x86_64__ -m64
 
 cflags-y	:=
+cflags-kernel-y	:=
 cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
 cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
 cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic)
@@ -35,7 +36,7 @@ cflags-y += -m64
 cflags-y += -mno-red-zone
 cflags-y += -mcmodel=kernel
 cflags-y += -pipe
-cflags-$(CONFIG_REORDER) += -ffunction-sections
+cflags-kernel-$(CONFIG_REORDER) += -ffunction-sections
 # this makes reading assembly source easier, but produces worse code
 # actually it makes the kernel smaller too.
 cflags-y += -fno-reorder-blocks
@@ -55,6 +56,7 @@ cflags-y += $(call cc-option,-funit-at-a-time)
 cflags-y += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,)
 
 CFLAGS += $(cflags-y)
+CFLAGS_KERNEL += $(cflags-kernel-y)
 AFLAGS += -m64
 
 head-y := arch/x86_64/kernel/head.o arch/x86_64/kernel/head64.o arch/x86_64/kernel/init_task.o

arch/x86_64/boot/Makefile

@@ -107,8 +107,13 @@ fdimage288: $(BOOTIMAGE) $(obj)/mtools.conf
 isoimage: $(BOOTIMAGE)
 	-rm -rf $(obj)/isoimage
 	mkdir $(obj)/isoimage
-	cp `echo /usr/lib*/syslinux/isolinux.bin | awk '{ print $1; }'` \
-		$(obj)/isoimage
+	for i in lib lib64 share end ; do \
+		if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \
+			cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \
+			break ; \
+		fi ; \
+		if [ $$i = end ] ; then exit 1 ; fi ; \
+	done
 	cp $(BOOTIMAGE) $(obj)/isoimage/linux
 	echo '$(image_cmdline)' > $(obj)/isoimage/isolinux.cfg
 	if [ -f '$(FDINITRD)' ] ; then \

arch/x86_64/boot/compressed/misc.c

@@ -77,11 +77,11 @@ static void gzip_release(void **);
  */
 static unsigned char *real_mode; /* Pointer to real-mode data */
 
-#define EXT_MEM_K   (*(unsigned short *)(real_mode + 0x2))
+#define RM_EXT_MEM_K   (*(unsigned short *)(real_mode + 0x2))
 #ifndef STANDARD_MEMORY_BIOS_CALL
-#define ALT_MEM_K   (*(unsigned long *)(real_mode + 0x1e0))
+#define RM_ALT_MEM_K   (*(unsigned long *)(real_mode + 0x1e0))
 #endif
-#define SCREEN_INFO (*(struct screen_info *)(real_mode+0))
+#define RM_SCREEN_INFO (*(struct screen_info *)(real_mode+0))
 
 extern unsigned char input_data[];
 extern int input_len;
@@ -92,9 +92,9 @@ static unsigned long output_ptr = 0;
 
 static void *malloc(int size);
 static void free(void *where);
- 
-void* memset(void* s, int c, unsigned n);
-void* memcpy(void* dest, const void* src, unsigned n);
+
+static void *memset(void *s, int c, unsigned n);
+static void *memcpy(void *dest, const void *src, unsigned n);
 
 static void putstr(const char *);
 
@@ -162,8 +162,8 @@ static void putstr(const char *s)
 	int x,y,pos;
 	char c;
 
-	x = SCREEN_INFO.orig_x;
-	y = SCREEN_INFO.orig_y;
+	x = RM_SCREEN_INFO.orig_x;
+	y = RM_SCREEN_INFO.orig_y;
 
 	while ( ( c = *s++ ) != '\0' ) {
 		if ( c == '\n' ) {
@@ -184,8 +184,8 @@ static void putstr(const char *s)
 		}
 	}
 
-	SCREEN_INFO.orig_x = x;
-	SCREEN_INFO.orig_y = y;
+	RM_SCREEN_INFO.orig_x = x;
+	RM_SCREEN_INFO.orig_y = y;
 
 	pos = (x + cols * y) * 2;	/* Update cursor position */
 	outb_p(14, vidport);
@@ -194,7 +194,7 @@ static void putstr(const char *s)
 	outb_p(0xff & (pos >> 1), vidport+1);
 }
 
-void* memset(void* s, int c, unsigned n)
+static void* memset(void* s, int c, unsigned n)
 {
 	int i;
 	char *ss = (char*)s;
@@ -203,7 +203,7 @@ void* memset(void* s, int c, unsigned n)
 	return s;
 }
 
-void* memcpy(void* dest, const void* src, unsigned n)
+static void* memcpy(void* dest, const void* src, unsigned n)
 {
 	int i;
 	char *d = (char *)dest, *s = (char *)src;
@@ -278,15 +278,15 @@ static void error(char *x)
 	putstr(x);
 	putstr("\n\n -- System halted");
 
-	while(1);
+	while(1);	/* Halt */
 }
 
-void setup_normal_output_buffer(void)
+static void setup_normal_output_buffer(void)
 {
 #ifdef STANDARD_MEMORY_BIOS_CALL
-	if (EXT_MEM_K < 1024) error("Less than 2MB of memory");
+	if (RM_EXT_MEM_K < 1024) error("Less than 2MB of memory");
 #else
-	if ((ALT_MEM_K > EXT_MEM_K ? ALT_MEM_K : EXT_MEM_K) < 1024) error("Less than 2MB of memory");
+	if ((RM_ALT_MEM_K > RM_EXT_MEM_K ? RM_ALT_MEM_K : RM_EXT_MEM_K) < 1024) error("Less than 2MB of memory");
 #endif
 	output_data = (unsigned char *)__PHYSICAL_START; /* Normally Points to 1M */
 	free_mem_end_ptr = (long)real_mode;
@@ -297,13 +297,13 @@ struct moveparams {
 	uch *high_buffer_start; int hcount;
 };
 
-void setup_output_buffer_if_we_run_high(struct moveparams *mv)
+static void setup_output_buffer_if_we_run_high(struct moveparams *mv)
 {
 	high_buffer_start = (uch *)(((ulg)&end) + HEAP_SIZE);
 #ifdef STANDARD_MEMORY_BIOS_CALL
-	if (EXT_MEM_K < (3*1024)) error("Less than 4MB of memory");
+	if (RM_EXT_MEM_K < (3*1024)) error("Less than 4MB of memory");
 #else
-	if ((ALT_MEM_K > EXT_MEM_K ? ALT_MEM_K : EXT_MEM_K) < (3*1024)) error("Less than 4MB of memory");
+	if ((RM_ALT_MEM_K > RM_EXT_MEM_K ? RM_ALT_MEM_K : RM_EXT_MEM_K) < (3*1024)) error("Less than 4MB of memory");
 #endif	
 	mv->low_buffer_start = output_data = (unsigned char *)LOW_BUFFER_START;
 	low_buffer_end = ((unsigned int)real_mode > LOW_BUFFER_MAX
@@ -319,7 +319,7 @@ void setup_output_buffer_if_we_run_high(struct moveparams *mv)
 	mv->high_buffer_start = high_buffer_start;
 }
 
-void close_output_buffer_if_we_run_high(struct moveparams *mv)
+static void close_output_buffer_if_we_run_high(struct moveparams *mv)
 {
 	if (bytes_out > low_buffer_size) {
 		mv->lcount = low_buffer_size;
@@ -335,7 +335,7 @@ int decompress_kernel(struct moveparams *mv, void *rmode)
 {
 	real_mode = rmode;
 
-	if (SCREEN_INFO.orig_video_mode == 7) {
+	if (RM_SCREEN_INFO.orig_video_mode == 7) {
 		vidmem = (char *) 0xb0000;
 		vidport = 0x3b4;
 	} else {
@@ -343,8 +343,8 @@ int decompress_kernel(struct moveparams *mv, void *rmode)
 		vidport = 0x3d4;
 	}
 
-	lines = SCREEN_INFO.orig_video_lines;
-	cols = SCREEN_INFO.orig_video_cols;
+	lines = RM_SCREEN_INFO.orig_video_lines;
+	cols = RM_SCREEN_INFO.orig_video_cols;
 
 	if (free_mem_ptr < 0x100000) setup_normal_output_buffer();
 	else setup_output_buffer_if_we_run_high(mv);

arch/x86_64/boot/tools/build.c

@@ -149,10 +149,8 @@ int main(int argc, char ** argv)
 	sz = sb.st_size;
 	fprintf (stderr, "System is %d kB\n", sz/1024);
 	sys_size = (sz + 15) / 16;
-	/* 0x40000*16 = 4.0 MB, reasonable estimate for the current maximum */
-	if (sys_size > (is_big_kernel ? 0x40000 : DEF_SYSSIZE))
-		die("System is too big. Try using %smodules.",
-			is_big_kernel ? "" : "bzImage or ");
+	if (!is_big_kernel && sys_size > DEF_SYSSIZE)
+		die("System is too big. Try using bzImage or modules.");
 	while (sz > 0) {
 		int l, n;
 

arch/x86_64/defconfig

 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.17-rc1-git11
-# Sun Apr 16 07:22:36 2006
+# Linux kernel version: 2.6.17-git6
+# Sat Jun 24 00:52:28 2006
 #
 CONFIG_X86_64=y
 CONFIG_64BIT=y
@@ -42,7 +42,6 @@ CONFIG_IKCONFIG_PROC=y
 # CONFIG_RELAY is not set
 CONFIG_INITRAMFS_SOURCE=""
 CONFIG_UID16=y
-CONFIG_VM86=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_EMBEDDED is not set
 CONFIG_KALLSYMS=y
@@ -57,7 +56,6 @@ CONFIG_FUTEX=y
 CONFIG_EPOLL=y
 CONFIG_SHMEM=y
 CONFIG_SLAB=y
-CONFIG_DOUBLEFAULT=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
 # CONFIG_SLOB is not set
@@ -144,7 +142,8 @@ CONFIG_NR_CPUS=32
 CONFIG_HOTPLUG_CPU=y
 CONFIG_HPET_TIMER=y
 CONFIG_HPET_EMULATE_RTC=y
-CONFIG_GART_IOMMU=y
+CONFIG_IOMMU=y
+# CONFIG_CALGARY_IOMMU is not set
 CONFIG_SWIOTLB=y
 CONFIG_X86_MCE=y
 CONFIG_X86_MCE_INTEL=y
@@ -158,6 +157,7 @@ CONFIG_HZ_250=y
 # CONFIG_HZ_1000 is not set
 CONFIG_HZ=250
 # CONFIG_REORDER is not set
+CONFIG_K8_NB=y
 CONFIG_GENERIC_HARDIRQS=y
 CONFIG_GENERIC_IRQ_PROBE=y
 CONFIG_ISA_DMA_API=y
@@ -293,6 +293,8 @@ CONFIG_IP_PNP_DHCP=y
 # CONFIG_INET_IPCOMP is not set
 # CONFIG_INET_XFRM_TUNNEL is not set
 # CONFIG_INET_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
 CONFIG_INET_DIAG=y
 CONFIG_INET_TCP_DIAG=y
 # CONFIG_TCP_CONG_ADVANCED is not set
@@ -305,7 +307,10 @@ CONFIG_IPV6=y
 # CONFIG_INET6_IPCOMP is not set
 # CONFIG_INET6_XFRM_TUNNEL is not set
 # CONFIG_INET6_TUNNEL is not set
+# CONFIG_INET6_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET6_XFRM_MODE_TUNNEL is not set
 # CONFIG_IPV6_TUNNEL is not set
+# CONFIG_NETWORK_SECMARK is not set
 # CONFIG_NETFILTER is not set
 
 #
@@ -344,6 +349,7 @@ CONFIG_IPV6=y
 # Network testing
 #
 # CONFIG_NET_PKTGEN is not set
+# CONFIG_NET_TCPPROBE is not set
 # CONFIG_HAMRADIO is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
@@ -360,6 +366,7 @@ CONFIG_STANDALONE=y
 CONFIG_PREVENT_FIRMWARE_BUILD=y
 CONFIG_FW_LOADER=y
 # CONFIG_DEBUG_DRIVER is not set
+# CONFIG_SYS_HYPERVISOR is not set
 
 #
 # Connector - unified userspace <-> kernelspace linker
@@ -526,6 +533,7 @@ CONFIG_SCSI_ATA_PIIX=y
 # CONFIG_SCSI_SATA_MV is not set
 CONFIG_SCSI_SATA_NV=y
 # CONFIG_SCSI_PDC_ADMA is not set
+# CONFIG_SCSI_HPTIOP is not set
 # CONFIG_SCSI_SATA_QSTOR is not set
 # CONFIG_SCSI_SATA_PROMISE is not set
 # CONFIG_SCSI_SATA_SX4 is not set
@@ -591,10 +599,7 @@ CONFIG_IEEE1394=y
 #
 # Device Drivers
 #
-
-#
-# Texas Instruments PCILynx requires I2C
-#
+# CONFIG_IEEE1394_PCILYNX is not set
 CONFIG_IEEE1394_OHCI1394=y
 
 #
@@ -645,7 +650,16 @@ CONFIG_VORTEX=y
 #
 # Tulip family network device support
 #
-# CONFIG_NET_TULIP is not set
+CONFIG_NET_TULIP=y
+# CONFIG_DE2104X is not set
+CONFIG_TULIP=y
+# CONFIG_TULIP_MWI is not set
+# CONFIG_TULIP_MMIO is not set
+# CONFIG_TULIP_NAPI is not set
+# CONFIG_DE4X5 is not set
+# CONFIG_WINBOND_840 is not set
+# CONFIG_DM9102 is not set
+# CONFIG_ULI526X is not set
 # CONFIG_HP100 is not set
 CONFIG_NET_PCI=y
 # CONFIG_PCNET32 is not set
@@ -697,6 +711,7 @@ CONFIG_TIGON3=y
 # CONFIG_IXGB is not set
 CONFIG_S2IO=m
 # CONFIG_S2IO_NAPI is not set
+# CONFIG_MYRI10GE is not set
 
 #
 # Token Ring devices
@@ -887,7 +902,56 @@ CONFIG_HPET_MMAP=y
 #
 # I2C support
 #
-# CONFIG_I2C is not set
+CONFIG_I2C=m
+CONFIG_I2C_CHARDEV=m
+
+#
+# I2C Algorithms
+#
+# CONFIG_I2C_ALGOBIT is not set
+# CONFIG_I2C_ALGOPCF is not set
+# CONFIG_I2C_ALGOPCA is not set
+
+#
+# I2C Hardware Bus support
+#
+# CONFIG_I2C_ALI1535 is not set
+# CONFIG_I2C_ALI1563 is not set
+# CONFIG_I2C_ALI15X3 is not set
+# CONFIG_I2C_AMD756 is not set
+# CONFIG_I2C_AMD8111 is not set
+# CONFIG_I2C_I801 is not set
+# CONFIG_I2C_I810 is not set
+# CONFIG_I2C_PIIX4 is not set
+CONFIG_I2C_ISA=m
+# CONFIG_I2C_NFORCE2 is not set
+# CONFIG_I2C_OCORES is not set
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_PROSAVAGE is not set
+# CONFIG_I2C_SAVAGE4 is not set
+# CONFIG_I2C_SIS5595 is not set
+# CONFIG_I2C_SIS630 is not set
+# CONFIG_I2C_SIS96X is not set
+# CONFIG_I2C_STUB is not set
+# CONFIG_I2C_VIA is not set
+# CONFIG_I2C_VIAPRO is not set
+# CONFIG_I2C_VOODOO3 is not set
+# CONFIG_I2C_PCA_ISA is not set
+
+#
+# Miscellaneous I2C Chip support
+#
+# CONFIG_SENSORS_DS1337 is not set
+# CONFIG_SENSORS_DS1374 is not set
+# CONFIG_SENSORS_EEPROM is not set
+# CONFIG_SENSORS_PCF8574 is not set
+# CONFIG_SENSORS_PCA9539 is not set
+# CONFIG_SENSORS_PCF8591 is not set
+# CONFIG_SENSORS_MAX6875 is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_I2C_DEBUG_CHIP is not set
 
 #
 # SPI support
@@ -898,14 +962,51 @@ CONFIG_HPET_MMAP=y
 #
 # Dallas's 1-wire bus
 #
-# CONFIG_W1 is not set
 
 #
 # Hardware Monitoring support
 #
 CONFIG_HWMON=y
 # CONFIG_HWMON_VID is not set
+# CONFIG_SENSORS_ABITUGURU is not set
+# CONFIG_SENSORS_ADM1021 is not set
+# CONFIG_SENSORS_ADM1025 is not set
+# CONFIG_SENSORS_ADM1026 is not set
+# CONFIG_SENSORS_ADM1031 is not set
+# CONFIG_SENSORS_ADM9240 is not set
+# CONFIG_SENSORS_ASB100 is not set
+# CONFIG_SENSORS_ATXP1 is not set
+# CONFIG_SENSORS_DS1621 is not set
 # CONFIG_SENSORS_F71805F is not set
+# CONFIG_SENSORS_FSCHER is not set
+# CONFIG_SENSORS_FSCPOS is not set
+# CONFIG_SENSORS_GL518SM is not set
+# CONFIG_SENSORS_GL520SM is not set
+# CONFIG_SENSORS_IT87 is not set
+# CONFIG_SENSORS_LM63 is not set
+# CONFIG_SENSORS_LM75 is not set
+# CONFIG_SENSORS_LM77 is not set
+# CONFIG_SENSORS_LM78 is not set
+# CONFIG_SENSORS_LM80 is not set
+# CONFIG_SENSORS_LM83 is not set
+# CONFIG_SENSORS_LM85 is not set
+# CONFIG_SENSORS_LM87 is not set
+# CONFIG_SENSORS_LM90 is not set
+# CONFIG_SENSORS_LM92 is not set
+# CONFIG_SENSORS_MAX1619 is not set
+# CONFIG_SENSORS_PC87360 is not set
+# CONFIG_SENSORS_SIS5595 is not set
+# CONFIG_SENSORS_SMSC47M1 is not set
+# CONFIG_SENSORS_SMSC47M192 is not set
+CONFIG_SENSORS_SMSC47B397=m
+# CONFIG_SENSORS_VIA686A is not set
+# CONFIG_SENSORS_VT8231 is not set
+# CONFIG_SENSORS_W83781D is not set
+# CONFIG_SENSORS_W83791D is not set
+# CONFIG_SENSORS_W83792D is not set
+# CONFIG_SENSORS_W83L785TS is not set
+# CONFIG_SENSORS_W83627HF is not set
+# CONFIG_SENSORS_W83627EHF is not set
 # CONFIG_SENSORS_HDAPS is not set
 # CONFIG_HWMON_DEBUG_CHIP is not set
 
@@ -918,6 +1019,7 @@ CONFIG_HWMON=y
 # Multimedia devices
 #
 # CONFIG_VIDEO_DEV is not set
+CONFIG_VIDEO_V4L2=y
 
 #
 # Digital Video Broadcasting Devices
@@ -953,28 +1055,17 @@ CONFIG_SOUND=y
 # Open Sound System
 #
 CONFIG_SOUND_PRIME=y
-CONFIG_OBSOLETE_OSS_DRIVER=y
 # CONFIG_SOUND_BT878 is not set
-# CONFIG_SOUND_CMPCI is not set
 # CONFIG_SOUND_EMU10K1 is not set
 # CONFIG_SOUND_FUSION is not set
-# CONFIG_SOUND_CS4281 is not set
-# CONFIG_SOUND_ES1370 is not set
 # CONFIG_SOUND_ES1371 is not set
-# CONFIG_SOUND_ESSSOLO1 is not set
-# CONFIG_SOUND_MAESTRO is not set
-# CONFIG_SOUND_MAESTRO3 is not set
 CONFIG_SOUND_ICH=y
-# CONFIG_SOUND_SONICVIBES is not set
 # CONFIG_SOUND_TRIDENT is not set
 # CONFIG_SOUND_MSNDCLAS is not set
 # CONFIG_SOUND_MSNDPIN is not set
 # CONFIG_SOUND_VIA82CXXX is not set
 # CONFIG_SOUND_OSS is not set
-# CONFIG_SOUND_ALI5455 is not set
-# CONFIG_SOUND_FORTE is not set
-# CONFIG_SOUND_RME96XX is not set
-# CONFIG_SOUND_AD1980 is not set
+# CONFIG_SOUND_TVMIXER is not set
 
 #
 # USB support
@@ -1000,6 +1091,7 @@ CONFIG_USB_DEVICEFS=y
 CONFIG_USB_EHCI_HCD=y
 # CONFIG_USB_EHCI_SPLIT_ISO is not set
 # CONFIG_USB_EHCI_ROOT_HUB_TT is not set
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
 # CONFIG_USB_ISP116X_HCD is not set
 CONFIG_USB_OHCI_HCD=y
 # CONFIG_USB_OHCI_BIG_ENDIAN is not set
@@ -1089,10 +1181,12 @@ CONFIG_USB_MON=y
 # CONFIG_USB_LEGOTOWER is not set
 # CONFIG_USB_LCD is not set
 # CONFIG_USB_LED is not set
+# CONFIG_USB_CY7C63 is not set
 # CONFIG_USB_CYTHERM is not set
 # CONFIG_USB_PHIDGETKIT is not set
 # CONFIG_USB_PHIDGETSERVO is not set
 # CONFIG_USB_IDMOUSE is not set
+# CONFIG_USB_APPLEDISPLAY is not set
 # CONFIG_USB_SISUSBVGA is not set
 # CONFIG_USB_LD is not set
 # CONFIG_USB_TEST is not set
@@ -1140,6 +1234,19 @@ CONFIG_USB_MON=y
 #
 # CONFIG_RTC_CLASS is not set
 
+#
+# DMA Engine support
+#
+# CONFIG_DMA_ENGINE is not set
+
+#
+# DMA Clients
+#
+
+#
+# DMA Devices
+#
+
 #
 # Firmware Drivers
 #
@@ -1175,6 +1282,7 @@ CONFIG_FS_POSIX_ACL=y
 # CONFIG_MINIX_FS is not set
 # CONFIG_ROMFS_FS is not set
 CONFIG_INOTIFY=y
+CONFIG_INOTIFY_USER=y
 # CONFIG_QUOTA is not set
 CONFIG_DNOTIFY=y
 CONFIG_AUTOFS_FS=y
@@ -1331,7 +1439,8 @@ CONFIG_DETECT_SOFTLOCKUP=y
 CONFIG_DEBUG_FS=y
 # CONFIG_DEBUG_VM is not set
 # CONFIG_FRAME_POINTER is not set
-# CONFIG_UNWIND_INFO is not set
+CONFIG_UNWIND_INFO=y
+CONFIG_STACK_UNWIND=y
 # CONFIG_FORCED_INLINING is not set
 # CONFIG_RCU_TORTURE_TEST is not set
 # CONFIG_DEBUG_RODATA is not set

arch/x86_64/ia32/fpu32.c

@@ -2,7 +2,6 @@
  * Copyright 2002 Andi Kleen, SuSE Labs.
  * FXSAVE<->i387 conversion support. Based on code by Gareth Hughes.
  * This is used for ptrace, signals and coredumps in 32bit emulation.
- * $Id: fpu32.c,v 1.1 2002/03/21 14:16:32 ak Exp $
  */ 
 
 #include <linux/sched.h>

arch/x86_64/ia32/ia32_signal.c

@@ -6,8 +6,6 @@
  *  1997-11-28  Modified for POSIX.1b signals by Richard Henderson
  *  2000-06-20  Pentium III FXSR, SSE support by Gareth Hughes
  *  2000-12-*   x86-64 compatibility mode signal handling by Andi Kleen
- * 
- *  $Id: ia32_signal.c,v 1.22 2002/07/29 10:34:03 ak Exp $
  */
 
 #include <linux/sched.h>

arch/x86_64/ia32/ia32entry.S

@@ -155,6 +155,7 @@ sysenter_tracesys:
 	.previous
 	jmp	sysenter_do_call
 	CFI_ENDPROC
+ENDPROC(ia32_sysenter_target)
 
 /*
  * 32bit SYSCALL instruction entry.
@@ -178,7 +179,7 @@ sysenter_tracesys:
  */ 	
 ENTRY(ia32_cstar_target)
 	CFI_STARTPROC32	simple
-	CFI_DEF_CFA	rsp,0
+	CFI_DEF_CFA	rsp,PDA_STACKOFFSET
 	CFI_REGISTER	rip,rcx
 	/*CFI_REGISTER	rflags,r11*/
 	swapgs
@@ -249,6 +250,7 @@ cstar_tracesys:
 	.quad 1b,ia32_badarg
 	.previous
 	jmp cstar_do_call
+END(ia32_cstar_target)
 				
 ia32_badarg:
 	movq $-EFAULT,%rax
@@ -314,16 +316,13 @@ ia32_tracesys:
 	LOAD_ARGS ARGOFFSET  /* reload args from stack in case ptrace changed it */
 	RESTORE_REST
 	jmp ia32_do_syscall
+END(ia32_syscall)
 
 ia32_badsys:
 	movq $0,ORIG_RAX-ARGOFFSET(%rsp)
 	movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
 	jmp int_ret_from_sys_call
 
-ni_syscall:
-	movq %rax,%rdi
-	jmp  sys32_ni_syscall			
-
 quiet_ni_syscall:
 	movq $-ENOSYS,%rax
 	ret
@@ -370,10 +369,10 @@ ENTRY(ia32_ptregs_common)
 	RESTORE_REST
 	jmp  ia32_sysret	/* misbalances the return cache */
 	CFI_ENDPROC
+END(ia32_ptregs_common)
 
 	.section .rodata,"a"
 	.align 8
-	.globl ia32_sys_call_table
 ia32_sys_call_table:
 	.quad sys_restart_syscall
 	.quad sys_exit

arch/x86_64/ia32/ptrace32.c

@@ -7,8 +7,6 @@
  * 
  * This allows to access 64bit processes too; but there is no way to see the extended 
  * register contents.
- *
- * $Id: ptrace32.c,v 1.16 2003/03/14 16:06:35 ak Exp $
  */ 
 
 #include <linux/kernel.h>
@@ -27,6 +25,7 @@
 #include <asm/debugreg.h>
 #include <asm/i387.h>
 #include <asm/fpu32.h>
+#include <asm/ia32.h>
 
 /*
  * Determines which flags the user has access to [1 = access, 0 = no access].
@@ -199,6 +198,24 @@ static int getreg32(struct task_struct *child, unsigned regno, u32 *val)
 
 #undef R32
 
+static long ptrace32_siginfo(unsigned request, u32 pid, u32 addr, u32 data)
+{
+	int ret;
+	compat_siginfo_t *si32 = (compat_siginfo_t *)compat_ptr(data);
+	siginfo_t *si = compat_alloc_user_space(sizeof(siginfo_t));
+	if (request == PTRACE_SETSIGINFO) {
+		ret = copy_siginfo_from_user32(si, si32);
+		if (ret)
+			return ret;
+	}
+	ret = sys_ptrace(request, pid, addr, (unsigned long)si);
+	if (ret)
+		return ret;
+	if (request == PTRACE_GETSIGINFO)
+		ret = copy_siginfo_to_user32(si32, si);
+	return ret;
+}
+
 asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 {
 	struct task_struct *child;
@@ -208,9 +225,19 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 	__u32 val;
 
 	switch (request) { 
-	default:
+	case PTRACE_TRACEME:
+	case PTRACE_ATTACH:
+	case PTRACE_KILL:
+	case PTRACE_CONT:
+	case PTRACE_SINGLESTEP:
+	case PTRACE_DETACH:
+	case PTRACE_SYSCALL:
+	case PTRACE_SETOPTIONS:
 		return sys_ptrace(request, pid, addr, data); 
 
+	default:
+		return -EINVAL;
+
 	case PTRACE_PEEKTEXT:
 	case PTRACE_PEEKDATA:
 	case PTRACE_POKEDATA:
@@ -225,10 +252,11 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 	case PTRACE_GETFPXREGS:
 	case PTRACE_GETEVENTMSG:
 		break;
-	} 
 
-	if (request == PTRACE_TRACEME)
-		return ptrace_traceme();
+	case PTRACE_SETSIGINFO:
+	case PTRACE_GETSIGINFO:
+		return ptrace32_siginfo(request, pid, addr, data);
+	}
 
 	child = ptrace_get_task_struct(pid);
 	if (IS_ERR(child))
@@ -349,8 +377,7 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 		break;
 
 	default:
-		ret = -EINVAL;
-		break;
+		BUG();
 	}
 
  out:

arch/x86_64/ia32/sys_ia32.c

@@ -508,19 +508,6 @@ sys32_waitpid(compat_pid_t pid, unsigned int *stat_addr, int options)
 	return compat_sys_wait4(pid, stat_addr, options, NULL);
 }
 
-int sys32_ni_syscall(int call)
-{ 
-	struct task_struct *me = current;
-	static char lastcomm[sizeof(me->comm)];
-
-	if (strncmp(lastcomm, me->comm, sizeof(lastcomm))) {
-		printk(KERN_INFO "IA32 syscall %d from %s not implemented\n",
-		       call, me->comm);
-		strncpy(lastcomm, me->comm, sizeof(lastcomm));
-	} 
-	return -ENOSYS;	       
-} 
-
 /* 32-bit timeval and related flotsam.  */
 
 asmlinkage long
@@ -916,7 +903,7 @@ long sys32_vm86_warning(void)
 	struct task_struct *me = current;
 	static char lastcomm[sizeof(me->comm)];
 	if (strncmp(lastcomm, me->comm, sizeof(lastcomm))) {
-		printk(KERN_INFO "%s: vm86 mode not supported on 64 bit kernel\n",
+		compat_printk(KERN_INFO "%s: vm86 mode not supported on 64 bit kernel\n",
 		       me->comm);
 		strncpy(lastcomm, me->comm, sizeof(lastcomm));
 	} 
@@ -929,13 +916,3 @@ long sys32_lookup_dcookie(u32 addr_low, u32 addr_high,
 	return sys_lookup_dcookie(((u64)addr_high << 32) | addr_low, buf, len);
 }
 
-static int __init ia32_init (void)
-{
-	printk("IA32 emulation $Id: sys_ia32.c,v 1.32 2002/03/24 13:02:28 ak Exp $\n");  
-	return 0;
-}
-
-__initcall(ia32_init);
-
-extern unsigned long ia32_sys_call_table[];
-EXPORT_SYMBOL(ia32_sys_call_table);

arch/x86_64/kernel/Makefile

@@ -8,7 +8,7 @@ obj-y	:= process.o signal.o entry.o traps.o irq.o \
 		ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_x86_64.o \
 		x8664_ksyms.o i387.o syscall.o vsyscall.o \
 		setup64.o bootflag.o e820.o reboot.o quirks.o i8237.o \
-		pci-dma.o pci-nommu.o
+		pci-dma.o pci-nommu.o alternative.o
 
 obj-$(CONFIG_X86_MCE)         += mce.o
 obj-$(CONFIG_X86_MCE_INTEL)	+= mce_intel.o
@@ -28,11 +28,13 @@ obj-$(CONFIG_PM)		+= suspend.o
 obj-$(CONFIG_SOFTWARE_SUSPEND)	+= suspend_asm.o
 obj-$(CONFIG_CPU_FREQ)		+= cpufreq/
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
-obj-$(CONFIG_GART_IOMMU)	+= pci-gart.o aperture.o
+obj-$(CONFIG_IOMMU)		+= pci-gart.o aperture.o
+obj-$(CONFIG_CALGARY_IOMMU)	+= pci-calgary.o tce.o
 obj-$(CONFIG_SWIOTLB)		+= pci-swiotlb.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_X86_PM_TIMER)	+= pmtimer.o
 obj-$(CONFIG_X86_VSMP)		+= vsmp.o
+obj-$(CONFIG_K8_NB)		+= k8.o
 
 obj-$(CONFIG_MODULES)		+= module.o
 
@@ -49,3 +51,5 @@ intel_cacheinfo-y		+= ../../i386/kernel/cpu/intel_cacheinfo.o
 quirks-y			+= ../../i386/kernel/quirks.o
 i8237-y				+= ../../i386/kernel/i8237.o
 msr-$(subst m,y,$(CONFIG_X86_MSR))  += ../../i386/kernel/msr.o
+alternative-y			+= ../../i386/kernel/alternative.o
+

arch/x86_64/kernel/aperture.c

@@ -8,7 +8,6 @@
  * because only the bootmem allocator can allocate 32+MB. 
  * 
  * Copyright 2002 Andi Kleen, SuSE Labs.
- * $Id: aperture.c,v 1.7 2003/08/01 03:36:18 ak Exp $
  */
 #include <linux/config.h>
 #include <linux/kernel.h>
@@ -24,6 +23,7 @@
 #include <asm/proto.h>
 #include <asm/pci-direct.h>
 #include <asm/dma.h>
+#include <asm/k8.h>
 
 int iommu_aperture;
 int iommu_aperture_disabled __initdata = 0;
@@ -37,8 +37,6 @@ int fix_aperture __initdata = 1;
 /* This code runs before the PCI subsystem is initialized, so just
    access the northbridge directly. */
 
-#define NB_ID_3 (PCI_VENDOR_ID_AMD | (0x1103<<16))
-
 static u32 __init allocate_aperture(void) 
 {
 	pg_data_t *nd0 = NODE_DATA(0);
@@ -68,20 +66,20 @@ static u32 __init allocate_aperture(void)
 	return (u32)__pa(p); 
 }
 
-static int __init aperture_valid(char *name, u64 aper_base, u32 aper_size) 
+static int __init aperture_valid(u64 aper_base, u32 aper_size)
 { 
 	if (!aper_base) 
 		return 0;
 	if (aper_size < 64*1024*1024) { 
-		printk("Aperture from %s too small (%d MB)\n", name, aper_size>>20); 
+		printk("Aperture too small (%d MB)\n", aper_size>>20);
 		return 0;
 	}
 	if (aper_base + aper_size >= 0xffffffff) { 
-		printk("Aperture from %s beyond 4GB. Ignoring.\n",name);
+		printk("Aperture beyond 4GB. Ignoring.\n");
 		return 0; 
 	}
 	if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
-		printk("Aperture from %s pointing to e820 RAM. Ignoring.\n",name);
+		printk("Aperture pointing to e820 RAM. Ignoring.\n");
 		return 0; 
 	} 
 	return 1;
@@ -140,7 +138,7 @@ static __u32 __init read_agp(int num, int slot, int func, int cap, u32 *order)
 	printk("Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n", 
 	       aper, 32 << *order, apsizereg);
 
-	if (!aperture_valid("AGP bridge", aper, (32*1024*1024) << *order))
+	if (!aperture_valid(aper, (32*1024*1024) << *order))
 	    return 0;
 	return (u32)aper; 
 } 
@@ -208,10 +206,10 @@ void __init iommu_hole_init(void)
 
 	fix = 0;
 	for (num = 24; num < 32; num++) {		
-		char name[30];
-		if (read_pci_config(0, num, 3, 0x00) != NB_ID_3) 
-			continue;	
+		if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
+			continue;
 
+		iommu_detected = 1;
 		iommu_aperture = 1; 
 
 		aper_order = (read_pci_config(0, num, 3, 0x90) >> 1) & 7; 
@@ -222,9 +220,7 @@ void __init iommu_hole_init(void)
 		printk("CPU %d: aperture @ %Lx size %u MB\n", num-24, 
 		       aper_base, aper_size>>20);
 		
-		sprintf(name, "northbridge cpu %d", num-24); 
-
-		if (!aperture_valid(name, aper_base, aper_size)) { 
+		if (!aperture_valid(aper_base, aper_size)) {
 			fix = 1; 
 			break; 
 		}
@@ -273,7 +269,7 @@ void __init iommu_hole_init(void)
 
 	/* Fix up the north bridges */
 	for (num = 24; num < 32; num++) { 		
-		if (read_pci_config(0, num, 3, 0x00) != NB_ID_3) 
+		if (!early_is_k8_nb(read_pci_config(0, num, 3, 0x00)))
 			continue;	
 
 		/* Don't enable translation yet. That is done later. 

arch/x86_64/kernel/apic.c

@@ -100,7 +100,7 @@ void clear_local_APIC(void)
 	maxlvt = get_maxlvt();
 
 	/*
-	 * Masking an LVT entry on a P6 can trigger a local APIC error
+	 * Masking an LVT entry can trigger a local APIC error
 	 * if the vector is zero. Mask LVTERR first to prevent this.
 	 */
 	if (maxlvt >= 3) {
@@ -851,7 +851,18 @@ void disable_APIC_timer(void)
 		unsigned long v;
 
 		v = apic_read(APIC_LVTT);
-		apic_write(APIC_LVTT, v | APIC_LVT_MASKED);
+		/*
+		 * When an illegal vector value (0-15) is written to an LVT
+		 * entry and delivery mode is Fixed, the APIC may signal an
+		 * illegal vector error, with out regard to whether the mask
+		 * bit is set or whether an interrupt is actually seen on input.
+		 *
+		 * Boot sequence might call this function when the LVTT has
+		 * '0' vector value. So make sure vector field is set to
+		 * valid value.
+		 */
+		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+		apic_write(APIC_LVTT, v);
 	}
 }
 
@@ -909,15 +920,13 @@ int setup_profiling_timer(unsigned int multiplier)
 	return -EINVAL;
 }
 
-#ifdef CONFIG_X86_MCE_AMD
-void setup_threshold_lvt(unsigned long lvt_off)
+void setup_APIC_extened_lvt(unsigned char lvt_off, unsigned char vector,
+			    unsigned char msg_type, unsigned char mask)
 {
-	unsigned int v = 0;
-	unsigned long reg = (lvt_off << 4) + 0x500;
-	v |= THRESHOLD_APIC_VECTOR;
+	unsigned long reg = (lvt_off << 4) + K8_APIC_EXT_LVT_BASE;
+	unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
 	apic_write(reg, v);
 }
-#endif /* CONFIG_X86_MCE_AMD */
 
 #undef APIC_DIVISOR
 
@@ -983,7 +992,7 @@ void smp_apic_timer_interrupt(struct pt_regs *regs)
 }
 
 /*
- * oem_force_hpet_timer -- force HPET mode for some boxes.
+ * apic_is_clustered_box() -- Check if we can expect good TSC
  *
  * Thus far, the major user of this is IBM's Summit2 series:
  *
@@ -991,7 +1000,7 @@ void smp_apic_timer_interrupt(struct pt_regs *regs)
  * multi-chassis. Use available data to take a good guess.
  * If in doubt, go HPET.
  */
-__cpuinit int oem_force_hpet_timer(void)
+__cpuinit int apic_is_clustered_box(void)
 {
 	int i, clusters, zeros;
 	unsigned id;
@@ -1022,8 +1031,7 @@ __cpuinit int oem_force_hpet_timer(void)
 	}
 
 	/*
-	 * If clusters > 2, then should be multi-chassis.  Return 1 for HPET.
-	 * Else return 0 to use TSC.
+	 * If clusters > 2, then should be multi-chassis.
 	 * May have to revisit this when multi-core + hyperthreaded CPUs come
 	 * out, but AFAIK this will work even for them.
 	 */

arch/x86_64/kernel/crash.c

@@ -111,14 +111,14 @@ static int crash_nmi_callback(struct pt_regs *regs, int cpu)
 	atomic_dec(&waiting_for_crash_ipi);
 	/* Assume hlt works */
 	for(;;)
-		asm("hlt");
+		halt();
 
 	return 1;
 }
 
 static void smp_send_nmi_allbutself(void)
 {
-	send_IPI_allbutself(APIC_DM_NMI);
+	send_IPI_allbutself(NMI_VECTOR);
 }
 
 /*

arch/x86_64/kernel/e820.c

 /* 
  * Handle the memory map.
  * The functions here do the job until bootmem takes over.
- * $Id: e820.c,v 1.4 2002/09/19 19:25:32 ak Exp $
  *
  *  Getting sanitize_e820_map() in sync with i386 version by applying change:
  *  -  Provisions for empty E820 memory regions (reported by certain BIOSes).
@@ -621,6 +620,7 @@ void __init parse_memmapopt(char *p, char **from)
 }
 
 unsigned long pci_mem_start = 0xaeedbabe;
+EXPORT_SYMBOL(pci_mem_start);
 
 /*
  * Search for the biggest gap in the low 32 bits of the e820

arch/x86_64/kernel/entry.S

@@ -154,6 +154,7 @@ rff_trace:
 	GET_THREAD_INFO(%rcx)	
 	jmp rff_action
 	CFI_ENDPROC
+END(ret_from_fork)
 
 /*
  * System call entry. Upto 6 arguments in registers are supported.
@@ -188,7 +189,7 @@ rff_trace:
 
 ENTRY(system_call)
 	CFI_STARTPROC	simple
-	CFI_DEF_CFA	rsp,0
+	CFI_DEF_CFA	rsp,PDA_STACKOFFSET
 	CFI_REGISTER	rip,rcx
 	/*CFI_REGISTER	rflags,r11*/
 	swapgs
@@ -285,6 +286,7 @@ tracesys:
 	/* Use IRET because user could have changed frame */
 	jmp int_ret_from_sys_call
 	CFI_ENDPROC
+END(system_call)
 		
 /* 
  * Syscall return path ending with IRET.
@@ -364,6 +366,7 @@ int_restore_rest:
 	cli
 	jmp int_with_check
 	CFI_ENDPROC
+END(int_ret_from_sys_call)
 		
 /* 
  * Certain special system calls that need to save a complete full stack frame.
@@ -375,6 +378,7 @@ int_restore_rest:
 	leaq	\func(%rip),%rax
 	leaq    -ARGOFFSET+8(%rsp),\arg /* 8 for return address */
 	jmp	ptregscall_common
+END(\label)
 	.endm
 
 	CFI_STARTPROC
@@ -404,6 +408,7 @@ ENTRY(ptregscall_common)
 	CFI_REL_OFFSET rip, 0
 	ret
 	CFI_ENDPROC
+END(ptregscall_common)
 	
 ENTRY(stub_execve)
 	CFI_STARTPROC
@@ -418,6 +423,7 @@ ENTRY(stub_execve)
 	RESTORE_REST
 	jmp int_ret_from_sys_call
 	CFI_ENDPROC
+END(stub_execve)
 	
 /*
  * sigreturn is special because it needs to restore all registers on return.
@@ -435,6 +441,7 @@ ENTRY(stub_rt_sigreturn)
 	RESTORE_REST
 	jmp int_ret_from_sys_call
 	CFI_ENDPROC
+END(stub_rt_sigreturn)
 
 /*
  * initial frame state for interrupts and exceptions
@@ -466,29 +473,18 @@ ENTRY(stub_rt_sigreturn)
 /* 0(%rsp): interrupt number */ 
 	.macro interrupt func
 	cld
-#ifdef CONFIG_DEBUG_INFO
-	SAVE_ALL	
-	movq %rsp,%rdi
-	/*
-	 * Setup a stack frame pointer.  This allows gdb to trace
-	 * back to the original stack.
-	 */
-	movq %rsp,%rbp
-	CFI_DEF_CFA_REGISTER	rbp
-#else		
 	SAVE_ARGS
 	leaq -ARGOFFSET(%rsp),%rdi	# arg1 for handler
-#endif	
+	pushq %rbp
+	CFI_ADJUST_CFA_OFFSET	8
+	CFI_REL_OFFSET		rbp, 0
+	movq %rsp,%rbp
+	CFI_DEF_CFA_REGISTER	rbp
 	testl $3,CS(%rdi)
 	je 1f
 	swapgs	
 1:	incl	%gs:pda_irqcount	# RED-PEN should check preempt count
-	movq %gs:pda_irqstackptr,%rax
-	cmoveq %rax,%rsp /*todo This needs CFI annotation! */
-	pushq %rdi			# save old stack	
-#ifndef CONFIG_DEBUG_INFO
-	CFI_ADJUST_CFA_OFFSET	8
-#endif
+	cmoveq %gs:pda_irqstackptr,%rsp
 	call \func
 	.endm
 
@@ -497,17 +493,11 @@ ENTRY(common_interrupt)
 	interrupt do_IRQ
 	/* 0(%rsp): oldrsp-ARGOFFSET */
 ret_from_intr:
-	popq  %rdi
-#ifndef CONFIG_DEBUG_INFO
-	CFI_ADJUST_CFA_OFFSET	-8
-#endif
 	cli	
 	decl %gs:pda_irqcount
-#ifdef CONFIG_DEBUG_INFO
-	movq RBP(%rdi),%rbp
+	leaveq
 	CFI_DEF_CFA_REGISTER	rsp
-#endif
-	leaq ARGOFFSET(%rdi),%rsp /*todo This needs CFI annotation! */
+	CFI_ADJUST_CFA_OFFSET	-8
 exit_intr:
 	GET_THREAD_INFO(%rcx)
 	testl $3,CS-ARGOFFSET(%rsp)
@@ -589,7 +579,9 @@ retint_kernel:
 	call preempt_schedule_irq
 	jmp exit_intr
 #endif	
+
 	CFI_ENDPROC
+END(common_interrupt)
 	
 /*
  * APIC interrupts.
@@ -605,17 +597,21 @@ retint_kernel:
 
 ENTRY(thermal_interrupt)
 	apicinterrupt THERMAL_APIC_VECTOR,smp_thermal_interrupt
+END(thermal_interrupt)
 
 ENTRY(threshold_interrupt)
 	apicinterrupt THRESHOLD_APIC_VECTOR,mce_threshold_interrupt
+END(threshold_interrupt)
 
 #ifdef CONFIG_SMP	
 ENTRY(reschedule_interrupt)
 	apicinterrupt RESCHEDULE_VECTOR,smp_reschedule_interrupt
+END(reschedule_interrupt)
 
 	.macro INVALIDATE_ENTRY num
 ENTRY(invalidate_interrupt\num)
 	apicinterrupt INVALIDATE_TLB_VECTOR_START+\num,smp_invalidate_interrupt	
+END(invalidate_interrupt\num)
 	.endm
 
 	INVALIDATE_ENTRY 0
@@ -629,17 +625,21 @@ ENTRY(invalidate_interrupt\num)
 
 ENTRY(call_function_interrupt)
 	apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt
+END(call_function_interrupt)
 #endif
 
 #ifdef CONFIG_X86_LOCAL_APIC	
 ENTRY(apic_timer_interrupt)
 	apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt
+END(apic_timer_interrupt)
 
 ENTRY(error_interrupt)
 	apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt
+END(error_interrupt)
 
 ENTRY(spurious_interrupt)
 	apicinterrupt SPURIOUS_APIC_VECTOR,smp_spurious_interrupt
+END(spurious_interrupt)
 #endif
 				
 /*
@@ -777,6 +777,7 @@ error_kernelspace:
 	cmpq $gs_change,RIP(%rsp)
         je   error_swapgs
 	jmp  error_sti
+END(error_entry)
 	
        /* Reload gs selector with exception handling */
        /* edi:  new selector */ 
@@ -794,6 +795,7 @@ gs_change:
 	CFI_ADJUST_CFA_OFFSET -8
         ret
 	CFI_ENDPROC
+ENDPROC(load_gs_index)
        
         .section __ex_table,"a"
         .align 8
@@ -847,7 +849,7 @@ ENTRY(kernel_thread)
 	UNFAKE_STACK_FRAME
 	ret
 	CFI_ENDPROC
-
+ENDPROC(kernel_thread)
 	
 child_rip:
 	/*
@@ -860,6 +862,7 @@ child_rip:
 	# exit
 	xorl %edi, %edi
 	call do_exit
+ENDPROC(child_rip)
 
 /*
  * execve(). This function needs to use IRET, not SYSRET, to set up all state properly.
@@ -889,19 +892,24 @@ ENTRY(execve)
 	UNFAKE_STACK_FRAME
 	ret
 	CFI_ENDPROC
+ENDPROC(execve)
 
 KPROBE_ENTRY(page_fault)
 	errorentry do_page_fault
+END(page_fault)
 	.previous .text
 
 ENTRY(coprocessor_error)
 	zeroentry do_coprocessor_error
+END(coprocessor_error)
 
 ENTRY(simd_coprocessor_error)
 	zeroentry do_simd_coprocessor_error	
+END(simd_coprocessor_error)
 
 ENTRY(device_not_available)
 	zeroentry math_state_restore
+END(device_not_available)
 
 	/* runs on exception stack */
 KPROBE_ENTRY(debug)
@@ -911,6 +919,7 @@ KPROBE_ENTRY(debug)
 	paranoidentry do_debug, DEBUG_STACK
 	jmp paranoid_exit
 	CFI_ENDPROC
+END(debug)
 	.previous .text
 
 	/* runs on exception stack */	
@@ -961,6 +970,7 @@ paranoid_schedule:
 	cli
 	jmp paranoid_userspace
 	CFI_ENDPROC
+END(nmi)
 	.previous .text
 
 KPROBE_ENTRY(int3)
@@ -970,22 +980,28 @@ KPROBE_ENTRY(int3)
  	paranoidentry do_int3, DEBUG_STACK
  	jmp paranoid_exit
  	CFI_ENDPROC
+END(int3)
 	.previous .text
 
 ENTRY(overflow)
 	zeroentry do_overflow
+END(overflow)
 
 ENTRY(bounds)
 	zeroentry do_bounds
+END(bounds)
 
 ENTRY(invalid_op)
 	zeroentry do_invalid_op	
+END(invalid_op)
 
 ENTRY(coprocessor_segment_overrun)
 	zeroentry do_coprocessor_segment_overrun
+END(coprocessor_segment_overrun)
 
 ENTRY(reserved)
 	zeroentry do_reserved
+END(reserved)
 
 	/* runs on exception stack */
 ENTRY(double_fault)
@@ -993,12 +1009,15 @@ ENTRY(double_fault)
 	paranoidentry do_double_fault
 	jmp paranoid_exit
 	CFI_ENDPROC
+END(double_fault)
 
 ENTRY(invalid_TSS)
 	errorentry do_invalid_TSS
+END(invalid_TSS)
 
 ENTRY(segment_not_present)
 	errorentry do_segment_not_present
+END(segment_not_present)
 
 	/* runs on exception stack */
 ENTRY(stack_segment)
@@ -1006,19 +1025,24 @@ ENTRY(stack_segment)
 	paranoidentry do_stack_segment
 	jmp paranoid_exit
 	CFI_ENDPROC
+END(stack_segment)
 
 KPROBE_ENTRY(general_protection)
 	errorentry do_general_protection
+END(general_protection)
 	.previous .text
 
 ENTRY(alignment_check)
 	errorentry do_alignment_check
+END(alignment_check)
 
 ENTRY(divide_error)
 	zeroentry do_divide_error
+END(divide_error)
 
 ENTRY(spurious_interrupt_bug)
 	zeroentry do_spurious_interrupt_bug
+END(spurious_interrupt_bug)
 
 #ifdef CONFIG_X86_MCE
 	/* runs on exception stack */
@@ -1029,6 +1053,7 @@ ENTRY(machine_check)
 	paranoidentry do_machine_check
 	jmp paranoid_exit
 	CFI_ENDPROC
+END(machine_check)
 #endif
 
 ENTRY(call_softirq)
@@ -1046,3 +1071,37 @@ ENTRY(call_softirq)
 	decl %gs:pda_irqcount
 	ret
 	CFI_ENDPROC
+ENDPROC(call_softirq)
+
+#ifdef CONFIG_STACK_UNWIND
+ENTRY(arch_unwind_init_running)
+	CFI_STARTPROC
+	movq	%r15, R15(%rdi)
+	movq	%r14, R14(%rdi)
+	xchgq	%rsi, %rdx
+	movq	%r13, R13(%rdi)
+	movq	%r12, R12(%rdi)
+	xorl	%eax, %eax
+	movq	%rbp, RBP(%rdi)
+	movq	%rbx, RBX(%rdi)
+	movq	(%rsp), %rcx
+	movq	%rax, R11(%rdi)
+	movq	%rax, R10(%rdi)
+	movq	%rax, R9(%rdi)
+	movq	%rax, R8(%rdi)
+	movq	%rax, RAX(%rdi)
+	movq	%rax, RCX(%rdi)
+	movq	%rax, RDX(%rdi)
+	movq	%rax, RSI(%rdi)
+	movq	%rax, RDI(%rdi)
+	movq	%rax, ORIG_RAX(%rdi)
+	movq	%rcx, RIP(%rdi)
+	leaq	8(%rsp), %rcx
+	movq	$__KERNEL_CS, CS(%rdi)
+	movq	%rax, EFLAGS(%rdi)
+	movq	%rcx, RSP(%rdi)
+	movq	$__KERNEL_DS, SS(%rdi)
+	jmpq	*%rdx
+	CFI_ENDPROC
+ENDPROC(arch_unwind_init_running)
+#endif

arch/x86_64/kernel/genapic_flat.c

@@ -78,22 +78,29 @@ static void flat_send_IPI_mask(cpumask_t cpumask, int vector)
 
 static void flat_send_IPI_allbutself(int vector)
 {
-#ifndef CONFIG_HOTPLUG_CPU
-	if (((num_online_cpus()) - 1) >= 1)
-		__send_IPI_shortcut(APIC_DEST_ALLBUT, vector,APIC_DEST_LOGICAL);
+#ifdef	CONFIG_HOTPLUG_CPU
+	int hotplug = 1;
 #else
-	cpumask_t allbutme = cpu_online_map;
+	int hotplug = 0;
+#endif
+	if (hotplug || vector == NMI_VECTOR) {
+		cpumask_t allbutme = cpu_online_map;
 
-	cpu_clear(smp_processor_id(), allbutme);
+		cpu_clear(smp_processor_id(), allbutme);
 
-	if (!cpus_empty(allbutme))
-		flat_send_IPI_mask(allbutme, vector);
-#endif
+		if (!cpus_empty(allbutme))
+			flat_send_IPI_mask(allbutme, vector);
+	} else if (num_online_cpus() > 1) {
+		__send_IPI_shortcut(APIC_DEST_ALLBUT, vector,APIC_DEST_LOGICAL);
+	}
 }
 
 static void flat_send_IPI_all(int vector)
 {
-	__send_IPI_shortcut(APIC_DEST_ALLINC, vector, APIC_DEST_LOGICAL);
+	if (vector == NMI_VECTOR)
+		flat_send_IPI_mask(cpu_online_map, vector);
+	else
+		__send_IPI_shortcut(APIC_DEST_ALLINC, vector, APIC_DEST_LOGICAL);
 }
 
 static int flat_apic_id_registered(void)
@@ -108,10 +115,7 @@ static unsigned int flat_cpu_mask_to_apicid(cpumask_t cpumask)
 
 static unsigned int phys_pkg_id(int index_msb)
 {
-	u32 ebx;
-
-	ebx = cpuid_ebx(1);
-	return ((ebx >> 24) & 0xFF) >> index_msb;
+	return hard_smp_processor_id() >> index_msb;
 }
 
 struct genapic apic_flat =  {

arch/x86_64/kernel/head64.c

@@ -2,8 +2,6 @@
  *  linux/arch/x86_64/kernel/head64.c -- prepare to run common code
  *
  *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
- *
- *  $Id: head64.c,v 1.22 2001/07/06 14:28:20 ak Exp $
  */
 
 #include <linux/init.h>

arch/x86_64/kernel/i8259.c

@@ -44,11 +44,11 @@
 	BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
 	BI(x,c) BI(x,d) BI(x,e) BI(x,f)
 
-#define BUILD_14_IRQS(x) \
+#define BUILD_15_IRQS(x) \
 	BI(x,0) BI(x,1) BI(x,2) BI(x,3) \
 	BI(x,4) BI(x,5) BI(x,6) BI(x,7) \
 	BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
-	BI(x,c) BI(x,d)
+	BI(x,c) BI(x,d) BI(x,e)
 
 /*
  * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
@@ -73,13 +73,13 @@ BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb)
 BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd)
 
 #ifdef CONFIG_PCI_MSI
-	BUILD_14_IRQS(0xe)
+	BUILD_15_IRQS(0xe)
 #endif
 
 #endif
 
 #undef BUILD_16_IRQS
-#undef BUILD_14_IRQS
+#undef BUILD_15_IRQS
 #undef BI
 
 
@@ -92,11 +92,11 @@ BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd)
 	IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
 	IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f)
 
-#define IRQLIST_14(x) \
+#define IRQLIST_15(x) \
 	IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \
 	IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \
 	IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
-	IRQ(x,c), IRQ(x,d)
+	IRQ(x,c), IRQ(x,d), IRQ(x,e)
 
 void (*interrupt[NR_IRQS])(void) = {
 	IRQLIST_16(0x0),
@@ -108,7 +108,7 @@ void (*interrupt[NR_IRQS])(void) = {
 	IRQLIST_16(0xc), IRQLIST_16(0xd)
 
 #ifdef CONFIG_PCI_MSI
-	, IRQLIST_14(0xe)
+	, IRQLIST_15(0xe)
 #endif
 
 #endif

arch/x86_64/kernel/io_apic.c

@@ -41,6 +41,7 @@
 #include <asm/mach_apic.h>
 #include <asm/acpi.h>
 #include <asm/dma.h>
+#include <asm/nmi.h>
 
 #define __apicdebuginit  __init
 
@@ -56,6 +57,7 @@ int timer_over_8254 __initdata = 0;
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 
 static DEFINE_SPINLOCK(ioapic_lock);
+static DEFINE_SPINLOCK(vector_lock);
 
 /*
  * # of IRQ routing registers
@@ -317,7 +319,7 @@ void __init check_ioapic(void)
 				vendor &= 0xffff;
 				switch (vendor) { 
 				case PCI_VENDOR_ID_VIA:
-#ifdef CONFIG_GART_IOMMU
+#ifdef CONFIG_IOMMU
 					if ((end_pfn > MAX_DMA32_PFN ||
 					     force_iommu) &&
 					    !iommu_aperture_allowed) {
@@ -834,10 +836,17 @@ u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 };
 int assign_irq_vector(int irq)
 {
 	static int current_vector = FIRST_DEVICE_VECTOR, offset = 0;
+	unsigned long flags;
+	int vector;
 
 	BUG_ON(irq != AUTO_ASSIGN && (unsigned)irq >= NR_IRQ_VECTORS);
-	if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0)
+
+	spin_lock_irqsave(&vector_lock, flags);
+
+	if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0) {
+		spin_unlock_irqrestore(&vector_lock, flags);
 		return IO_APIC_VECTOR(irq);
+	}
 next:
 	current_vector += 8;
 	if (current_vector == IA32_SYSCALL_VECTOR)
@@ -849,11 +858,14 @@ int assign_irq_vector(int irq)
 		current_vector = FIRST_DEVICE_VECTOR + offset;
 	}
 
-	vector_irq[current_vector] = irq;
+	vector = current_vector;
+	vector_irq[vector] = irq;
 	if (irq != AUTO_ASSIGN)
-		IO_APIC_VECTOR(irq) = current_vector;
+		IO_APIC_VECTOR(irq) = vector;
+
+	spin_unlock_irqrestore(&vector_lock, flags);
 
-	return current_vector;
+	return vector;
 }
 
 extern void (*interrupt[NR_IRQS])(void);
@@ -866,21 +878,14 @@ static struct hw_interrupt_type ioapic_edge_type;
 
 static inline void ioapic_register_intr(int irq, int vector, unsigned long trigger)
 {
-	if (use_pci_vector() && !platform_legacy_irq(irq)) {
-		if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
-				trigger == IOAPIC_LEVEL)
-			irq_desc[vector].handler = &ioapic_level_type;
-		else
-			irq_desc[vector].handler = &ioapic_edge_type;
-		set_intr_gate(vector, interrupt[vector]);
-	} else	{
-		if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
-				trigger == IOAPIC_LEVEL)
-			irq_desc[irq].handler = &ioapic_level_type;
-		else
-			irq_desc[irq].handler = &ioapic_edge_type;
-		set_intr_gate(vector, interrupt[irq]);
-	}
+	unsigned idx = use_pci_vector() && !platform_legacy_irq(irq) ? vector : irq;
+
+	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
+			trigger == IOAPIC_LEVEL)
+		irq_desc[idx].handler = &ioapic_level_type;
+	else
+		irq_desc[idx].handler = &ioapic_edge_type;
+	set_intr_gate(vector, interrupt[idx]);
 }
 
 static void __init setup_IO_APIC_irqs(void)

arch/x86_64/kernel/irq.c

@@ -26,6 +26,30 @@ atomic_t irq_mis_count;
 #endif
 #endif
 
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+/*
+ * Probabilistic stack overflow check:
+ *
+ * Only check the stack in process context, because everything else
+ * runs on the big interrupt stacks. Checking reliably is too expensive,
+ * so we just check from interrupts.
+ */
+static inline void stack_overflow_check(struct pt_regs *regs)
+{
+	u64 curbase = (u64) current->thread_info;
+	static unsigned long warned = -60*HZ;
+
+	if (regs->rsp >= curbase && regs->rsp <= curbase + THREAD_SIZE &&
+	    regs->rsp <  curbase + sizeof(struct thread_info) + 128 &&
+	    time_after(jiffies, warned + 60*HZ)) {
+		printk("do_IRQ: %s near stack overflow (cur:%Lx,rsp:%lx)\n",
+		       current->comm, curbase, regs->rsp);
+		show_stack(NULL,NULL);
+		warned = jiffies;
+	}
+}
+#endif
+
 /*
  * Generic, controller-independent functions:
  */
@@ -39,7 +63,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (i == 0) {
 		seq_printf(p, "           ");
 		for_each_online_cpu(j)
-			seq_printf(p, "CPU%d       ",j);
+			seq_printf(p, "CPU%-8d",j);
 		seq_putc(p, '\n');
 	}
 
@@ -96,7 +120,9 @@ asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 
 	exit_idle();
 	irq_enter();
-
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+	stack_overflow_check(regs);
+#endif
 	__do_IRQ(irq, regs);
 	irq_exit();
 

arch/x86_64/kernel/k8.c

+/*
+ * Shared support code for AMD K8 northbridges and derivates.
+ * Copyright 2006 Andi Kleen, SUSE Labs. Subject to GPLv2.
+ */
+#include <linux/gfp.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <asm/k8.h>
+
+int num_k8_northbridges;
+EXPORT_SYMBOL(num_k8_northbridges);
+
+static u32 *flush_words;
+
+struct pci_device_id k8_nb_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) },
+	{}
+};
+EXPORT_SYMBOL(k8_nb_ids);
+
+struct pci_dev **k8_northbridges;
+EXPORT_SYMBOL(k8_northbridges);
+
+static struct pci_dev *next_k8_northbridge(struct pci_dev *dev)
+{
+	do {
+		dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
+		if (!dev)
+			break;
+	} while (!pci_match_id(&k8_nb_ids[0], dev));
+	return dev;
+}
+
+int cache_k8_northbridges(void)
+{
+	int i;
+	struct pci_dev *dev;
+	if (num_k8_northbridges)
+		return 0;
+
+	num_k8_northbridges = 0;
+	dev = NULL;
+	while ((dev = next_k8_northbridge(dev)) != NULL)
+		num_k8_northbridges++;
+
+	k8_northbridges = kmalloc((num_k8_northbridges + 1) * sizeof(void *),
+				  GFP_KERNEL);
+	if (!k8_northbridges)
+		return -ENOMEM;
+
+	flush_words = kmalloc(num_k8_northbridges * sizeof(u32), GFP_KERNEL);
+	if (!flush_words) {
+		kfree(k8_northbridges);
+		return -ENOMEM;
+	}
+
+	dev = NULL;
+	i = 0;
+	while ((dev = next_k8_northbridge(dev)) != NULL) {
+		k8_northbridges[i++] = dev;
+		pci_read_config_dword(dev, 0x9c, &flush_words[i]);
+	}
+	k8_northbridges[i] = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cache_k8_northbridges);
+
+/* Ignores subdevice/subvendor but as far as I can figure out
+   they're useless anyways */
+int __init early_is_k8_nb(u32 device)
+{
+	struct pci_device_id *id;
+	u32 vendor = device & 0xffff;
+	device >>= 16;
+	for (id = k8_nb_ids; id->vendor; id++)
+		if (vendor == id->vendor && device == id->device)
+			return 1;
+	return 0;
+}
+
+void k8_flush_garts(void)
+{
+	int flushed, i;
+	unsigned long flags;
+	static DEFINE_SPINLOCK(gart_lock);
+
+	/* Avoid races between AGP and IOMMU. In theory it's not needed
+	   but I'm not sure if the hardware won't lose flush requests
+	   when another is pending. This whole thing is so expensive anyways
+	   that it doesn't matter to serialize more. -AK */
+	spin_lock_irqsave(&gart_lock, flags);
+	flushed = 0;
+	for (i = 0; i < num_k8_northbridges; i++) {
+		pci_write_config_dword(k8_northbridges[i], 0x9c,
+				       flush_words[i]|1);
+		flushed++;
+	}
+	for (i = 0; i < num_k8_northbridges; i++) {
+		u32 w;
+		/* Make sure the hardware actually executed the flush*/
+		for (;;) {
+			pci_read_config_dword(k8_northbridges[i],
+					      0x9c, &w);
+			if (!(w & 1))
+				break;
+			cpu_relax();
+		}
+	}
+	spin_unlock_irqrestore(&gart_lock, flags);
+	if (!flushed)
+		printk("nothing to flush?\n");
+}
+EXPORT_SYMBOL_GPL(k8_flush_garts);
+

arch/x86_64/kernel/mce.c

@@ -562,7 +562,7 @@ static struct sysdev_class mce_sysclass = {
 	set_kset_name("machinecheck"),
 };
 
-static DEFINE_PER_CPU(struct sys_device, device_mce);
+DEFINE_PER_CPU(struct sys_device, device_mce);
 
 /* Why are there no generic functions for this? */
 #define ACCESSOR(name, var, start) \

arch/x86_64/kernel/module.c

@@ -145,26 +145,38 @@ int apply_relocate(Elf_Shdr *sechdrs,
 	return -ENOSYS;
 } 
 
-extern void apply_alternatives(void *start, void *end); 
-
 int module_finalize(const Elf_Ehdr *hdr,
-		    const Elf_Shdr *sechdrs,
-		    struct module *me)
+                    const Elf_Shdr *sechdrs,
+                    struct module *me)
 {
-	const Elf_Shdr *s;
+	const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL;
 	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
-	/* look for .altinstructions to patch */ 
-	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { 
-		void *seg; 		
-		if (strcmp(".altinstructions", secstrings + s->sh_name))
-			continue;
-		seg = (void *)s->sh_addr; 
-		apply_alternatives(seg, seg + s->sh_size); 
-	} 	
+	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
+		if (!strcmp(".text", secstrings + s->sh_name))
+			text = s;
+		if (!strcmp(".altinstructions", secstrings + s->sh_name))
+			alt = s;
+		if (!strcmp(".smp_locks", secstrings + s->sh_name))
+			locks= s;
+	}
+
+	if (alt) {
+		/* patch .altinstructions */
+		void *aseg = (void *)alt->sh_addr;
+		apply_alternatives(aseg, aseg + alt->sh_size);
+	}
+	if (locks && text) {
+		void *lseg = (void *)locks->sh_addr;
+		void *tseg = (void *)text->sh_addr;
+		alternatives_smp_module_add(me, me->name,
+					    lseg, lseg + locks->sh_size,
+					    tseg, tseg + text->sh_size);
+	}
 	return 0;
 }
 
 void module_arch_cleanup(struct module *mod)
 {
+	alternatives_smp_module_del(mod);
 }

arch/x86_64/kernel/nmi.c

@@ -15,11 +15,7 @@
 #include <linux/config.h>
 #include <linux/mm.h>
 #include <linux/delay.h>
-#include <linux/bootmem.h>
-#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
-#include <linux/mc146818rtc.h>
-#include <linux/kernel_stat.h>
 #include <linux/module.h>
 #include <linux/sysdev.h>
 #include <linux/nmi.h>
@@ -27,14 +23,11 @@
 #include <linux/kprobes.h>
 
 #include <asm/smp.h>
-#include <asm/mtrr.h>
-#include <asm/mpspec.h>
 #include <asm/nmi.h>
-#include <asm/msr.h>
 #include <asm/proto.h>
 #include <asm/kdebug.h>
-#include <asm/local.h>
 #include <asm/mce.h>
+#include <asm/intel_arch_perfmon.h>
 
 /*
  * lapic_nmi_owner tracks the ownership of the lapic NMI hardware:
@@ -74,6 +67,9 @@ static unsigned int nmi_p4_cccr_val;
 #define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING	0x76
 #define K7_NMI_EVENT		K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING
 
+#define ARCH_PERFMON_NMI_EVENT_SEL	ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
+#define ARCH_PERFMON_NMI_EVENT_UMASK	ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
+
 #define MSR_P4_MISC_ENABLE	0x1A0
 #define MSR_P4_MISC_ENABLE_PERF_AVAIL	(1<<7)
 #define MSR_P4_MISC_ENABLE_PEBS_UNAVAIL	(1<<12)
@@ -105,7 +101,10 @@ static __cpuinit inline int nmi_known_cpu(void)
 	case X86_VENDOR_AMD:
 		return boot_cpu_data.x86 == 15;
 	case X86_VENDOR_INTEL:
-		return boot_cpu_data.x86 == 15;
+		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
+			return 1;
+		else
+			return (boot_cpu_data.x86 == 15);
 	}
 	return 0;
 }
@@ -211,6 +210,8 @@ int __init setup_nmi_watchdog(char *str)
 
 __setup("nmi_watchdog=", setup_nmi_watchdog);
 
+static void disable_intel_arch_watchdog(void);
+
 static void disable_lapic_nmi_watchdog(void)
 {
 	if (nmi_active <= 0)
@@ -223,6 +224,8 @@ static void disable_lapic_nmi_watchdog(void)
 		if (boot_cpu_data.x86 == 15) {
 			wrmsr(MSR_P4_IQ_CCCR0, 0, 0);
 			wrmsr(MSR_P4_CRU_ESCR0, 0, 0);
+		} else if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
+			disable_intel_arch_watchdog();
 		}
 		break;
 	}
@@ -375,6 +378,53 @@ static void setup_k7_watchdog(void)
 	wrmsr(MSR_K7_EVNTSEL0, evntsel, 0);
 }
 
+static void disable_intel_arch_watchdog(void)
+{
+	unsigned ebx;
+
+	/*
+	 * Check whether the Architectural PerfMon supports
+	 * Unhalted Core Cycles Event or not.
+	 * NOTE: Corresponding bit = 0 in ebp indicates event present.
+	 */
+	ebx = cpuid_ebx(10);
+	if (!(ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
+		wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, 0, 0);
+}
+
+static int setup_intel_arch_watchdog(void)
+{
+	unsigned int evntsel;
+	unsigned ebx;
+
+	/*
+	 * Check whether the Architectural PerfMon supports
+	 * Unhalted Core Cycles Event or not.
+	 * NOTE: Corresponding bit = 0 in ebp indicates event present.
+	 */
+	ebx = cpuid_ebx(10);
+	if ((ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
+		return 0;
+
+	nmi_perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0;
+
+	clear_msr_range(MSR_ARCH_PERFMON_EVENTSEL0, 2);
+	clear_msr_range(MSR_ARCH_PERFMON_PERFCTR0, 2);
+
+	evntsel = ARCH_PERFMON_EVENTSEL_INT
+		| ARCH_PERFMON_EVENTSEL_OS
+		| ARCH_PERFMON_EVENTSEL_USR
+		| ARCH_PERFMON_NMI_EVENT_SEL
+		| ARCH_PERFMON_NMI_EVENT_UMASK;
+
+	wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, evntsel, 0);
+	wrmsrl(MSR_ARCH_PERFMON_PERFCTR0, -((u64)cpu_khz * 1000 / nmi_hz));
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+	wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, evntsel, 0);
+	return 1;
+}
+
 
 static int setup_p4_watchdog(void)
 {
@@ -428,10 +478,16 @@ void setup_apic_nmi_watchdog(void)
 		setup_k7_watchdog();
 		break;
 	case X86_VENDOR_INTEL:
-		if (boot_cpu_data.x86 != 15)
-			return;
-		if (!setup_p4_watchdog())
+		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
+			if (!setup_intel_arch_watchdog())
+				return;
+		} else if (boot_cpu_data.x86 == 15) {
+			if (!setup_p4_watchdog())
+				return;
+		} else {
 			return;
+		}
+
 		break;
 
 	default:
@@ -516,7 +572,14 @@ void __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
  			 */
  			wrmsr(MSR_P4_IQ_CCCR0, nmi_p4_cccr_val, 0);
  			apic_write(APIC_LVTPC, APIC_DM_NMI);
- 		}
+ 		} else if (nmi_perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
+			/*
+			 * For Intel based architectural perfmon
+			 * - LVTPC is masked on interrupt and must be
+			 *   unmasked by the LVTPC handler.
+			 */
+			apic_write(APIC_LVTPC, APIC_DM_NMI);
+		}
 		wrmsrl(nmi_perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz));
 	}
 }

arch/x86_64/kernel/pci-dma.c

@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <asm/io.h>
 #include <asm/proto.h>
+#include <asm/calgary.h>
 
 int iommu_merge __read_mostly = 0;
 EXPORT_SYMBOL(iommu_merge);
@@ -33,12 +34,15 @@ int panic_on_overflow __read_mostly = 0;
 int force_iommu __read_mostly= 0;
 #endif
 
+/* Set this to 1 if there is a HW IOMMU in the system */
+int iommu_detected __read_mostly = 0;
+
 /* Dummy device used for NULL arguments (normally ISA). Better would
    be probably a smaller DMA mask, but this is bug-to-bug compatible
    to i386. */
 struct device fallback_dev = {
 	.bus_id = "fallback device",
-	.coherent_dma_mask = 0xffffffff,
+	.coherent_dma_mask = DMA_32BIT_MASK,
 	.dma_mask = &fallback_dev.coherent_dma_mask,
 };
 
@@ -77,7 +81,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		dev = &fallback_dev;
 	dma_mask = dev->coherent_dma_mask;
 	if (dma_mask == 0)
-		dma_mask = 0xffffffff;
+		dma_mask = DMA_32BIT_MASK;
 
 	/* Don't invoke OOM killer */
 	gfp |= __GFP_NORETRY;
@@ -90,7 +94,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	   larger than 16MB and in this case we have a chance of
 	   finding fitting memory in the next higher zone first. If
 	   not retry with true GFP_DMA. -AK */
-	if (dma_mask <= 0xffffffff)
+	if (dma_mask <= DMA_32BIT_MASK)
 		gfp |= GFP_DMA32;
 
  again:
@@ -111,7 +115,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 
 			/* Don't use the 16MB ZONE_DMA unless absolutely
 			   needed. It's better to use remapping first. */
-			if (dma_mask < 0xffffffff && !(gfp & GFP_DMA)) {
+			if (dma_mask < DMA_32BIT_MASK && !(gfp & GFP_DMA)) {
 				gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
 				goto again;
 			}
@@ -174,7 +178,7 @@ int dma_supported(struct device *dev, u64 mask)
 	/* Copied from i386. Doesn't make much sense, because it will
 	   only work for pci_alloc_coherent.
 	   The caller just has to use GFP_DMA in this case. */
-        if (mask < 0x00ffffff)
+        if (mask < DMA_24BIT_MASK)
                 return 0;
 
 	/* Tell the device to use SAC when IOMMU force is on.  This
@@ -189,7 +193,7 @@ int dma_supported(struct device *dev, u64 mask)
 	   SAC for these.  Assume all masks <= 40 bits are of this
 	   type. Normally this doesn't make any difference, but gives
 	   more gentle handling of IOMMU overflow. */
-	if (iommu_sac_force && (mask >= 0xffffffffffULL)) {
+	if (iommu_sac_force && (mask >= DMA_40BIT_MASK)) {
 		printk(KERN_INFO "%s: Force SAC with mask %Lx\n", dev->bus_id,mask);
 		return 0;
 	}
@@ -266,7 +270,7 @@ __init int iommu_setup(char *p)
 		    swiotlb = 1;
 #endif
 
-#ifdef CONFIG_GART_IOMMU
+#ifdef CONFIG_IOMMU
 	    gart_parse_options(p);
 #endif
 
@@ -276,3 +280,40 @@ __init int iommu_setup(char *p)
     }
     return 1;
 }
+__setup("iommu=", iommu_setup);
+
+void __init pci_iommu_alloc(void)
+{
+	/*
+	 * The order of these functions is important for
+	 * fall-back/fail-over reasons
+	 */
+#ifdef CONFIG_IOMMU
+	iommu_hole_init();
+#endif
+
+#ifdef CONFIG_CALGARY_IOMMU
+	detect_calgary();
+#endif
+
+#ifdef CONFIG_SWIOTLB
+	pci_swiotlb_init();
+#endif
+}
+
+static int __init pci_iommu_init(void)
+{
+#ifdef CONFIG_CALGARY_IOMMU
+	calgary_iommu_init();
+#endif
+
+#ifdef CONFIG_IOMMU
+	gart_iommu_init();
+#endif
+
+	no_iommu_init();
+	return 0;
+}
+
+/* Must execute after PCI subsystem */
+fs_initcall(pci_iommu_init);

arch/x86_64/kernel/pci-gart.c

@@ -32,6 +32,7 @@
 #include <asm/kdebug.h>
 #include <asm/swiotlb.h>
 #include <asm/dma.h>
+#include <asm/k8.h>
 
 unsigned long iommu_bus_base;	/* GART remapping area (physical) */
 static unsigned long iommu_size; 	/* size of remapping area bytes */
@@ -46,8 +47,6 @@ u32 *iommu_gatt_base; 		/* Remapping table */
    also seen with Qlogic at least). */
 int iommu_fullflush = 1;
 
-#define MAX_NB 8
-
 /* Allocation bitmap for the remapping area */ 
 static DEFINE_SPINLOCK(iommu_bitmap_lock);
 static unsigned long *iommu_gart_bitmap; /* guarded by iommu_bitmap_lock */
@@ -63,13 +62,6 @@ static u32 gart_unmapped_entry;
 #define to_pages(addr,size) \
 	(round_up(((addr) & ~PAGE_MASK) + (size), PAGE_SIZE) >> PAGE_SHIFT)
 
-#define for_all_nb(dev) \
-	dev = NULL;	\
-	while ((dev = pci_get_device(PCI_VENDOR_ID_AMD, 0x1103, dev))!=NULL)
-
-static struct pci_dev *northbridges[MAX_NB];
-static u32 northbridge_flush_word[MAX_NB];
-
 #define EMERGENCY_PAGES 32 /* = 128KB */ 
 
 #ifdef CONFIG_AGP
@@ -93,7 +85,7 @@ static unsigned long alloc_iommu(int size)
 	offset = find_next_zero_string(iommu_gart_bitmap,next_bit,iommu_pages,size);
 	if (offset == -1) {
 		need_flush = 1;
-	       	offset = find_next_zero_string(iommu_gart_bitmap,0,next_bit,size);
+		offset = find_next_zero_string(iommu_gart_bitmap,0,iommu_pages,size);
 	}
 	if (offset != -1) { 
 		set_bit_string(iommu_gart_bitmap, offset, size); 
@@ -120,44 +112,17 @@ static void free_iommu(unsigned long offset, int size)
 /* 
  * Use global flush state to avoid races with multiple flushers.
  */
-static void flush_gart(struct device *dev)
+static void flush_gart(void)
 { 
 	unsigned long flags;
-	int flushed = 0;
-	int i, max;
-
 	spin_lock_irqsave(&iommu_bitmap_lock, flags);
-	if (need_flush) { 
-		max = 0;
-		for (i = 0; i < MAX_NB; i++) {
-			if (!northbridges[i]) 
-				continue;
-			pci_write_config_dword(northbridges[i], 0x9c, 
-					       northbridge_flush_word[i] | 1); 
-			flushed++;
-			max = i;
-		}
-		for (i = 0; i <= max; i++) {
-			u32 w;
-			if (!northbridges[i])
-				continue;
-			/* Make sure the hardware actually executed the flush. */
-			for (;;) { 
-				pci_read_config_dword(northbridges[i], 0x9c, &w);
-				if (!(w & 1))
-					break;
-				cpu_relax();
-			}
-		} 
-		if (!flushed) 
-			printk("nothing to flush?\n");
+	if (need_flush) {
+		k8_flush_garts();
 		need_flush = 0;
 	} 
 	spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
 } 
 
-
-
 #ifdef CONFIG_IOMMU_LEAK
 
 #define SET_LEAK(x) if (iommu_leak_tab) \
@@ -266,7 +231,7 @@ static dma_addr_t gart_map_simple(struct device *dev, char *buf,
 				 size_t size, int dir)
 {
 	dma_addr_t map = dma_map_area(dev, virt_to_bus(buf), size, dir);
-	flush_gart(dev);
+	flush_gart();
 	return map;
 }
 
@@ -288,6 +253,28 @@ dma_addr_t gart_map_single(struct device *dev, void *addr, size_t size, int dir)
 	return bus; 
 }
 
+/*
+ * Free a DMA mapping.
+ */
+void gart_unmap_single(struct device *dev, dma_addr_t dma_addr,
+		      size_t size, int direction)
+{
+	unsigned long iommu_page;
+	int npages;
+	int i;
+
+	if (dma_addr < iommu_bus_base + EMERGENCY_PAGES*PAGE_SIZE ||
+	    dma_addr >= iommu_bus_base + iommu_size)
+		return;
+	iommu_page = (dma_addr - iommu_bus_base)>>PAGE_SHIFT;
+	npages = to_pages(dma_addr, size);
+	for (i = 0; i < npages; i++) {
+		iommu_gatt_base[iommu_page + i] = gart_unmapped_entry;
+		CLEAR_LEAK(iommu_page + i);
+	}
+	free_iommu(iommu_page, npages);
+}
+
 /*
  * Wrapper for pci_unmap_single working with scatterlists.
  */
@@ -299,7 +286,7 @@ void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int di
 		struct scatterlist *s = &sg[i];
 		if (!s->dma_length || !s->length)
 			break;
-		dma_unmap_single(dev, s->dma_address, s->dma_length, dir);
+		gart_unmap_single(dev, s->dma_address, s->dma_length, dir);
 	}
 }
 
@@ -329,7 +316,7 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg,
 		s->dma_address = addr;
 		s->dma_length = s->length;
 	}
-	flush_gart(dev);
+	flush_gart();
 	return nents;
 }
 
@@ -436,13 +423,13 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 	if (dma_map_cont(sg, start, i, sg+out, pages, need) < 0)
 		goto error;
 	out++;
-	flush_gart(dev);
+	flush_gart();
 	if (out < nents) 
 		sg[out].dma_length = 0; 
 	return out;
 
 error:
-	flush_gart(NULL);
+	flush_gart();
 	gart_unmap_sg(dev, sg, nents, dir);
 	/* When it was forced or merged try again in a dumb way */
 	if (force_iommu || iommu_merge) {
@@ -458,28 +445,6 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 	return 0;
 } 
 
-/*
- * Free a DMA mapping.
- */ 
-void gart_unmap_single(struct device *dev, dma_addr_t dma_addr,
-		      size_t size, int direction)
-{
-	unsigned long iommu_page; 
-	int npages;
-	int i;
-
-	if (dma_addr < iommu_bus_base + EMERGENCY_PAGES*PAGE_SIZE || 
-	    dma_addr >= iommu_bus_base + iommu_size)
-		return;
-	iommu_page = (dma_addr - iommu_bus_base)>>PAGE_SHIFT;	
-	npages = to_pages(dma_addr, size);
-	for (i = 0; i < npages; i++) { 
-		iommu_gatt_base[iommu_page + i] = gart_unmapped_entry; 
-		CLEAR_LEAK(iommu_page + i);
-	}
-	free_iommu(iommu_page, npages);
-}
-
 static int no_agp;
 
 static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size)
@@ -532,10 +497,13 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 	void *gatt;
 	unsigned aper_base, new_aper_base;
 	unsigned aper_size, gatt_size, new_aper_size;
-	
+	int i;
+
 	printk(KERN_INFO "PCI-DMA: Disabling AGP.\n");
 	aper_size = aper_base = info->aper_size = 0;
-	for_all_nb(dev) { 
+	dev = NULL;
+	for (i = 0; i < num_k8_northbridges; i++) {
+		dev = k8_northbridges[i];
 		new_aper_base = read_aperture(dev, &new_aper_size); 
 		if (!new_aper_base) 
 			goto nommu; 
@@ -558,11 +526,12 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 		panic("Cannot allocate GATT table"); 
 	memset(gatt, 0, gatt_size); 
 	agp_gatt_table = gatt;
-	
-	for_all_nb(dev) { 
+
+	for (i = 0; i < num_k8_northbridges; i++) {
 		u32 ctl; 
 		u32 gatt_reg; 
 
+		dev = k8_northbridges[i];
 		gatt_reg = __pa(gatt) >> 12; 
 		gatt_reg <<= 4; 
 		pci_write_config_dword(dev, 0x98, gatt_reg);
@@ -573,7 +542,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
 		pci_write_config_dword(dev, 0x90, ctl); 
 	}
-	flush_gart(NULL); 
+	flush_gart();
 	
 	printk("PCI-DMA: aperture base @ %x size %u KB\n",aper_base, aper_size>>10); 
 	return 0;
@@ -602,15 +571,19 @@ static struct dma_mapping_ops gart_dma_ops = {
 	.unmap_sg = gart_unmap_sg,
 };
 
-static int __init pci_iommu_init(void)
+void __init gart_iommu_init(void)
 { 
 	struct agp_kern_info info;
 	unsigned long aper_size;
 	unsigned long iommu_start;
-	struct pci_dev *dev;
 	unsigned long scratch;
 	long i;
 
+	if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) {
+		printk(KERN_INFO "PCI-GART: No AMD northbridge found.\n");
+		return;
+	}
+
 #ifndef CONFIG_AGP_AMD64
 	no_agp = 1; 
 #else
@@ -622,7 +595,11 @@ static int __init pci_iommu_init(void)
 #endif	
 
 	if (swiotlb)
-		return -1; 
+		return;
+
+	/* Did we detect a different HW IOMMU? */
+	if (iommu_detected && !iommu_aperture)
+		return;
 
 	if (no_iommu ||
 	    (!force_iommu && end_pfn <= MAX_DMA32_PFN) ||
@@ -634,15 +611,7 @@ static int __init pci_iommu_init(void)
 					"but IOMMU not available.\n"
 			       KERN_ERR "WARNING 32bit PCI may malfunction.\n");
 		}
-		return -1;
-	}
-
-	i = 0;
-	for_all_nb(dev)
-		i++;
-	if (i > MAX_NB) {
-		printk(KERN_ERR "PCI-GART: Too many northbridges (%ld). Disabled\n", i);
-		return -1;
+		return;
 	}
 
 	printk(KERN_INFO "PCI-DMA: using GART IOMMU.\n");
@@ -707,26 +676,10 @@ static int __init pci_iommu_init(void)
 	for (i = EMERGENCY_PAGES; i < iommu_pages; i++) 
 		iommu_gatt_base[i] = gart_unmapped_entry;
 
-	for_all_nb(dev) {
-		u32 flag; 
-		int cpu = PCI_SLOT(dev->devfn) - 24;
-		if (cpu >= MAX_NB)
-			continue;
-		northbridges[cpu] = dev;
-		pci_read_config_dword(dev, 0x9c, &flag); /* cache flush word */
-		northbridge_flush_word[cpu] = flag; 
-	}
-		     
-	flush_gart(NULL);
-
+	flush_gart();
 	dma_ops = &gart_dma_ops;
-
-	return 0;
 } 
 
-/* Must execute after PCI subsystem */
-fs_initcall(pci_iommu_init);
-
 void gart_parse_options(char *p)
 {
 	int arg;

arch/x86_64/kernel/pci-nommu.c

@@ -4,6 +4,8 @@
 #include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/string.h>
+#include <linux/dma-mapping.h>
+
 #include <asm/proto.h>
 #include <asm/processor.h>
 #include <asm/dma.h>
@@ -12,10 +14,11 @@ static int
 check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
 {
         if (hwdev && bus + size > *hwdev->dma_mask) {
-		if (*hwdev->dma_mask >= 0xffffffffULL)
+		if (*hwdev->dma_mask >= DMA_32BIT_MASK)
 			printk(KERN_ERR
-			    "nommu_%s: overflow %Lx+%lu of device mask %Lx\n",
-	       			name, (long long)bus, size, (long long)*hwdev->dma_mask);
+			    "nommu_%s: overflow %Lx+%zu of device mask %Lx\n",
+				name, (long long)bus, size,
+				(long long)*hwdev->dma_mask);
 		return 0;
 	}
 	return 1;

arch/x86_64/kernel/pci-swiotlb.c

@@ -31,7 +31,7 @@ struct dma_mapping_ops swiotlb_dma_ops = {
 void pci_swiotlb_init(void)
 {
 	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
-	if (!iommu_aperture && !no_iommu &&
+	if (!iommu_detected && !no_iommu &&
 	    (end_pfn > MAX_DMA32_PFN || force_iommu))
 	       swiotlb = 1;
 	if (swiotlb) {

arch/x86_64/kernel/process.c

@@ -10,7 +10,6 @@
  *	Andi Kleen.
  *
  *	CPU hotplug support - ashok.raj@intel.com
- *  $Id: process.c,v 1.38 2002/01/15 10:08:03 ak Exp $
  */
 
 /*
@@ -64,6 +63,7 @@ EXPORT_SYMBOL(boot_option_idle_override);
  * Powermanagement idle function, if any..
  */
 void (*pm_idle)(void);
+EXPORT_SYMBOL(pm_idle);
 static DEFINE_PER_CPU(unsigned int, cpu_idle_state);
 
 static ATOMIC_NOTIFIER_HEAD(idle_notifier);
@@ -111,7 +111,7 @@ static void default_idle(void)
 {
 	local_irq_enable();
 
-	clear_thread_flag(TIF_POLLING_NRFLAG);
+	current_thread_info()->status &= ~TS_POLLING;
 	smp_mb__after_clear_bit();
 	while (!need_resched()) {
 		local_irq_disable();
@@ -120,7 +120,7 @@ static void default_idle(void)
 		else
 			local_irq_enable();
 	}
-	set_thread_flag(TIF_POLLING_NRFLAG);
+	current_thread_info()->status |= TS_POLLING;
 }
 
 /*
@@ -203,8 +203,7 @@ static inline void play_dead(void)
  */
 void cpu_idle (void)
 {
-	set_thread_flag(TIF_POLLING_NRFLAG);
-
+	current_thread_info()->status |= TS_POLLING;
 	/* endless idle loop with no priority at all */
 	while (1) {
 		while (!need_resched()) {
@@ -335,7 +334,7 @@ void show_regs(struct pt_regs *regs)
 {
 	printk("CPU %d:", smp_processor_id());
 	__show_regs(regs);
-	show_trace(&regs->rsp);
+	show_trace(NULL, regs, (void *)(regs + 1));
 }
 
 /*
@@ -365,8 +364,11 @@ void flush_thread(void)
 	struct task_struct *tsk = current;
 	struct thread_info *t = current_thread_info();
 
-	if (t->flags & _TIF_ABI_PENDING)
+	if (t->flags & _TIF_ABI_PENDING) {
 		t->flags ^= (_TIF_ABI_PENDING | _TIF_IA32);
+		if (t->flags & _TIF_IA32)
+			current_thread_info()->status |= TS_COMPAT;
+	}
 
 	tsk->thread.debugreg0 = 0;
 	tsk->thread.debugreg1 = 0;

arch/x86_64/kernel/reboot.c

@@ -20,6 +20,7 @@
  * Power off function, if any
  */
 void (*pm_power_off)(void);
+EXPORT_SYMBOL(pm_power_off);
 
 static long no_idt[3];
 static enum { 

arch/x86_64/kernel/setup64.c

@@ -3,7 +3,6 @@
  * Copyright (C) 1995  Linus Torvalds
  * Copyright 2001, 2002, 2003 SuSE Labs / Andi Kleen.
  * See setup.c for older changelog.
- * $Id: setup64.c,v 1.12 2002/03/21 10:09:17 ak Exp $
  */ 
 #include <linux/config.h>
 #include <linux/init.h>
@@ -31,6 +30,7 @@ char x86_boot_params[BOOT_PARAM_SIZE] __initdata = {0,};
 cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
 
 struct x8664_pda *_cpu_pda[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(_cpu_pda);
 struct x8664_pda boot_cpu_pda[NR_CPUS] __cacheline_aligned;
 
 struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
@@ -38,6 +38,7 @@ struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
 char boot_cpu_stack[IRQSTACKSIZE] __attribute__((section(".bss.page_aligned")));
 
 unsigned long __supported_pte_mask __read_mostly = ~0UL;
+EXPORT_SYMBOL(__supported_pte_mask);
 static int do_not_nx __cpuinitdata = 0;
 
 /* noexec=on|off

arch/x86_64/kernel/signal.c

@@ -7,8 +7,6 @@
  *  1997-11-28  Modified for POSIX.1b signals by Richard Henderson
  *  2000-06-20  Pentium III FXSR, SSE support by Gareth Hughes
  *  2000-2002   x86-64 support by Andi Kleen
- * 
- *  $Id: signal.c,v 1.18 2001/10/17 22:30:37 ak Exp $
  */
 
 #include <linux/sched.h>
@@ -239,7 +237,6 @@ get_stack(struct k_sigaction *ka, struct pt_regs *regs, unsigned long size)
 	rsp = regs->rsp - 128;
 
 	/* This is the X/Open sanctioned signal stack switching.  */
-	/* RED-PEN: redzone on that stack? */
 	if (ka->sa.sa_flags & SA_ONSTACK) {
 		if (sas_ss_flags(rsp) == 0)
 			rsp = current->sas_ss_sp + current->sas_ss_size;

arch/x86_64/kernel/smp.c

@@ -224,6 +224,7 @@ void flush_tlb_current_task(void)
 		flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
 	preempt_enable();
 }
+EXPORT_SYMBOL(flush_tlb_current_task);
 
 void flush_tlb_mm (struct mm_struct * mm)
 {
@@ -244,6 +245,7 @@ void flush_tlb_mm (struct mm_struct * mm)
 
 	preempt_enable();
 }
+EXPORT_SYMBOL(flush_tlb_mm);
 
 void flush_tlb_page(struct vm_area_struct * vma, unsigned long va)
 {
@@ -266,6 +268,7 @@ void flush_tlb_page(struct vm_area_struct * vma, unsigned long va)
 
 	preempt_enable();
 }
+EXPORT_SYMBOL(flush_tlb_page);
 
 static void do_flush_tlb_all(void* info)
 {
@@ -443,6 +446,7 @@ int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
 	spin_unlock(&call_lock);
 	return 0;
 }
+EXPORT_SYMBOL(smp_call_function);
 
 void smp_stop_cpu(void)
 {
@@ -460,7 +464,7 @@ static void smp_really_stop_cpu(void *dummy)
 {
 	smp_stop_cpu(); 
 	for (;;) 
-		asm("hlt"); 
+		halt();
 } 
 
 void smp_send_stop(void)
@@ -520,13 +524,13 @@ asmlinkage void smp_call_function_interrupt(void)
 
 int safe_smp_processor_id(void)
 {
-	int apicid, i;
+	unsigned apicid, i;
 
 	if (disable_apic)
 		return 0;
 
 	apicid = hard_smp_processor_id();
-	if (x86_cpu_to_apicid[apicid] == apicid)
+	if (apicid < NR_CPUS && x86_cpu_to_apicid[apicid] == apicid)
 		return apicid;
 
 	for (i = 0; i < NR_CPUS; ++i) {

arch/x86_64/kernel/smpboot.c

@@ -63,13 +63,11 @@
 
 /* Number of siblings per CPU package */
 int smp_num_siblings = 1;
-/* Package ID of each logical CPU */
-u8 phys_proc_id[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID };
-/* core ID of each logical CPU */
-u8 cpu_core_id[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID };
+EXPORT_SYMBOL(smp_num_siblings);
 
 /* Last level cache ID of each logical CPU */
 u8 cpu_llc_id[NR_CPUS] __cpuinitdata  = {[0 ... NR_CPUS-1] = BAD_APICID};
+EXPORT_SYMBOL(cpu_llc_id);
 
 /* Bitmask of currently online CPUs */
 cpumask_t cpu_online_map __read_mostly;
@@ -82,18 +80,21 @@ EXPORT_SYMBOL(cpu_online_map);
  */
 cpumask_t cpu_callin_map;
 cpumask_t cpu_callout_map;
+EXPORT_SYMBOL(cpu_callout_map);
 
 cpumask_t cpu_possible_map;
 EXPORT_SYMBOL(cpu_possible_map);
 
 /* Per CPU bogomips and other parameters */
 struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned;
+EXPORT_SYMBOL(cpu_data);
 
 /* Set when the idlers are all forked */
 int smp_threads_ready;
 
 /* representing HT siblings of each logical CPU */
 cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(cpu_sibling_map);
 
 /* representing HT and core siblings of each logical CPU */
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
@@ -472,8 +473,8 @@ static inline void set_cpu_sibling_map(int cpu)
 
 	if (smp_num_siblings > 1) {
 		for_each_cpu_mask(i, cpu_sibling_setup_map) {
-			if (phys_proc_id[cpu] == phys_proc_id[i] &&
-			    cpu_core_id[cpu] == cpu_core_id[i]) {
+			if (c[cpu].phys_proc_id == c[i].phys_proc_id &&
+			    c[cpu].cpu_core_id == c[i].cpu_core_id) {
 				cpu_set(i, cpu_sibling_map[cpu]);
 				cpu_set(cpu, cpu_sibling_map[i]);
 				cpu_set(i, cpu_core_map[cpu]);
@@ -500,7 +501,7 @@ static inline void set_cpu_sibling_map(int cpu)
 			cpu_set(i, c[cpu].llc_shared_map);
 			cpu_set(cpu, c[i].llc_shared_map);
 		}
-		if (phys_proc_id[cpu] == phys_proc_id[i]) {
+		if (c[cpu].phys_proc_id == c[i].phys_proc_id) {
 			cpu_set(i, cpu_core_map[cpu]);
 			cpu_set(cpu, cpu_core_map[i]);
 			/*
@@ -797,6 +798,8 @@ static int __cpuinit do_boot_cpu(int cpu, int apicid)
 	}
 
 
+	alternatives_smp_switch(1);
+
 	c_idle.idle = get_idle_for_cpu(cpu);
 
 	if (c_idle.idle) {
@@ -1199,8 +1202,8 @@ static void remove_siblinginfo(int cpu)
 		cpu_clear(cpu, cpu_sibling_map[sibling]);
 	cpus_clear(cpu_sibling_map[cpu]);
 	cpus_clear(cpu_core_map[cpu]);
-	phys_proc_id[cpu] = BAD_APICID;
-	cpu_core_id[cpu] = BAD_APICID;
+	c[cpu].phys_proc_id = 0;
+	c[cpu].cpu_core_id = 0;
 	cpu_clear(cpu, cpu_sibling_setup_map);
 }
 
@@ -1259,6 +1262,8 @@ void __cpu_die(unsigned int cpu)
 		/* They ack this in play_dead by setting CPU_DEAD */
 		if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
 			printk ("CPU %d is now offline\n", cpu);
+			if (1 == num_online_cpus())
+				alternatives_smp_switch(0);
 			return;
 		}
 		msleep(100);

include/asm-i386/k8.h

+#include <asm-x86_64/k8.h>