Merge branch 'core/percpu' into percpu-cpumask-x86-for-linus-2

Conflicts:
	arch/parisc/kernel/irq.c
	arch/x86/include/asm/fixmap_64.h
	arch/x86/include/asm/setup.h
	kernel/irq/handle.c

Semantic merge:
        arch/x86/include/asm/fixmap.h

Signed-off-by: Ingo Molnar <mingo@elte.hu>

Documentation/cputopology.txt

@@ -18,11 +18,11 @@ For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
-#define topology_thread_siblings(cpu)
-#define topology_core_siblings(cpu)
+#define topology_thread_cpumask(cpu)
+#define topology_core_cpumask(cpu)
 
 The type of **_id is int.
-The type of siblings is cpumask_t.
+The type of siblings is (const) struct cpumask *.
 
 To be consistent on all architectures, include/linux/topology.h
 provides default definitions for any of the above macros that are

Documentation/kernel-parameters.txt

@@ -1325,8 +1325,13 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	memtest=	[KNL,X86] Enable memtest
 			Format: <integer>
-			range: 0,4 : pattern number
 			default : 0 <disable>
+			Specifies the number of memtest passes to be
+			performed. Each pass selects another test
+			pattern from a given set of patterns. Memtest
+			fills the memory with this pattern, validates
+			memory contents and reserves bad memory
+			regions that are detected.
 
 	meye.*=		[HW] Set MotionEye Camera parameters
 			See Documentation/video4linux/meye.txt.

Documentation/x86/boot.txt

@@ -158,7 +158,7 @@ Offset	Proto	Name		Meaning
 0202/4	2.00+	header		Magic signature "HdrS"
 0206/2	2.00+	version		Boot protocol version supported
 0208/4	2.00+	realmode_swtch	Boot loader hook (see below)
-020C/2	2.00+	start_sys	The load-low segment (0x1000) (obsolete)
+020C/2	2.00+	start_sys_seg	The load-low segment (0x1000) (obsolete)
 020E/2	2.00+	kernel_version	Pointer to kernel version string
 0210/1	2.00+	type_of_loader	Boot loader identifier
 0211/1	2.00+	loadflags	Boot protocol option flags
@@ -170,10 +170,11 @@ Offset	Proto	Name		Meaning
 0224/2	2.01+	heap_end_ptr	Free memory after setup end
 0226/2	N/A	pad1		Unused
 0228/4	2.02+	cmd_line_ptr	32-bit pointer to the kernel command line
-022C/4	2.03+	initrd_addr_max	Highest legal initrd address
+022C/4	2.03+	ramdisk_max	Highest legal initrd address
 0230/4	2.05+	kernel_alignment Physical addr alignment required for kernel
 0234/1	2.05+	relocatable_kernel Whether kernel is relocatable or not
-0235/3	N/A	pad2		Unused
+0235/1	N/A	pad2		Unused
+0236/2	N/A	pad3		Unused
 0238/4	2.06+	cmdline_size	Maximum size of the kernel command line
 023C/4	2.07+	hardware_subarch Hardware subarchitecture
 0240/8	2.07+	hardware_subarch_data Subarchitecture-specific data
@@ -299,14 +300,14 @@ Protocol:	2.00+
   e.g. 0x0204 for version 2.04, and 0x0a11 for a hypothetical version
   10.17.
 
-Field name:	readmode_swtch
+Field name:	realmode_swtch
 Type:		modify (optional)
 Offset/size:	0x208/4
 Protocol:	2.00+
 
   Boot loader hook (see ADVANCED BOOT LOADER HOOKS below.)
 
-Field name:	start_sys
+Field name:	start_sys_seg
 Type:		read
 Offset/size:	0x20c/2
 Protocol:	2.00+
@@ -468,7 +469,7 @@ Protocol:	2.02+
   zero, the kernel will assume that your boot loader does not support
   the 2.02+ protocol.
 
-Field name:	initrd_addr_max
+Field name:	ramdisk_max
 Type:		read
 Offset/size:	0x22c/4
 Protocol:	2.03+
@@ -542,7 +543,10 @@ Protocol:	2.08+
 
   The payload may be compressed. The format of both the compressed and
   uncompressed data should be determined using the standard magic
-  numbers. Currently only gzip compressed ELF is used.
+  numbers.  The currently supported compression formats are gzip
+  (magic numbers 1F 8B or 1F 9E), bzip2 (magic number 42 5A) and LZMA
+  (magic number 5D 00).  The uncompressed payload is currently always ELF
+  (magic number 7F 45 4C 46).
   
 Field name:	payload_length
 Type:		read

Makefile

@@ -533,8 +533,9 @@ KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN})
 endif
 
 # Force gcc to behave correct even for buggy distributions
-# Arch Makefiles may override this setting
+ifndef CONFIG_CC_STACKPROTECTOR
 KBUILD_CFLAGS += $(call cc-option, -fno-stack-protector)
+endif
 
 ifdef CONFIG_FRAME_POINTER
 KBUILD_CFLAGS	+= -fno-omit-frame-pointer -fno-optimize-sibling-calls

arch/alpha/kernel/irq.c

@@ -55,7 +55,7 @@ int irq_select_affinity(unsigned int irq)
 		cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0);
 	last_cpu = cpu;
 
-	irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+	cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
 	irq_desc[irq].chip->set_affinity(irq, cpumask_of(cpu));
 	return 0;
 }

arch/alpha/mm/init.c

@@ -189,9 +189,21 @@ callback_init(void * kernel_end)
 
 	if (alpha_using_srm) {
 		static struct vm_struct console_remap_vm;
-		unsigned long vaddr = VMALLOC_START;
+		unsigned long nr_pages = 0;
+		unsigned long vaddr;
 		unsigned long i, j;
 
+		/* calculate needed size */
+		for (i = 0; i < crb->map_entries; ++i)
+			nr_pages += crb->map[i].count;
+
+		/* register the vm area */
+		console_remap_vm.flags = VM_ALLOC;
+		console_remap_vm.size = nr_pages << PAGE_SHIFT;
+		vm_area_register_early(&console_remap_vm, PAGE_SIZE);
+
+		vaddr = (unsigned long)console_remap_vm.addr;
+
 		/* Set up the third level PTEs and update the virtual
 		   addresses of the CRB entries.  */
 		for (i = 0; i < crb->map_entries; ++i) {
@@ -213,12 +225,6 @@ callback_init(void * kernel_end)
 				vaddr += PAGE_SIZE;
 			}
 		}
-
-		/* Let vmalloc know that we've allocated some space.  */
-		console_remap_vm.flags = VM_ALLOC;
-		console_remap_vm.addr = (void *) VMALLOC_START;
-		console_remap_vm.size = vaddr - VMALLOC_START;
-		vmlist = &console_remap_vm;
 	}
 
 	callback_init_done = 1;

arch/arm/kernel/irq.c

@@ -104,6 +104,11 @@ static struct irq_desc bad_irq_desc = {
 	.lock = __SPIN_LOCK_UNLOCKED(bad_irq_desc.lock),
 };
 
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* We are not allocating bad_irq_desc.affinity or .pending_mask */
+#error "ARM architecture does not support CONFIG_CPUMASK_OFFSTACK."
+#endif
+
 /*
  * do_IRQ handles all hardware IRQ's.  Decoded IRQs should not
  * come via this function.  Instead, they should provide their
@@ -161,7 +166,7 @@ void __init init_IRQ(void)
 		irq_desc[irq].status |= IRQ_NOREQUEST | IRQ_NOPROBE;
 
 #ifdef CONFIG_SMP
-	bad_irq_desc.affinity = CPU_MASK_ALL;
+	cpumask_setall(bad_irq_desc.affinity);
 	bad_irq_desc.cpu = smp_processor_id();
 #endif
 	init_arch_irq();
@@ -191,15 +196,16 @@ void migrate_irqs(void)
 		struct irq_desc *desc = irq_desc + i;
 
 		if (desc->cpu == cpu) {
-			unsigned int newcpu = any_online_cpu(desc->affinity);
-
-			if (newcpu == NR_CPUS) {
+			unsigned int newcpu = cpumask_any_and(desc->affinity,
+							      cpu_online_mask);
+			if (newcpu >= nr_cpu_ids) {
 				if (printk_ratelimit())
 					printk(KERN_INFO "IRQ%u no longer affine to CPU%u\n",
 					       i, cpu);
 
-				cpus_setall(desc->affinity);
-				newcpu = any_online_cpu(desc->affinity);
+				cpumask_setall(desc->affinity);
+				newcpu = cpumask_any_and(desc->affinity,
+							 cpu_online_mask);
 			}
 
 			route_irq(desc, i, newcpu);

arch/arm/kernel/vmlinux.lds.S

@@ -64,7 +64,9 @@ SECTIONS
 		__initramfs_end = .;
 #endif
 		. = ALIGN(4096);
+		__per_cpu_load = .;
 		__per_cpu_start = .;
+			*(.data.percpu.page_aligned)
 			*(.data.percpu)
 			*(.data.percpu.shared_aligned)
 		__per_cpu_end = .;

arch/arm/oprofile/op_model_mpcore.c

@@ -263,7 +263,7 @@ static void em_route_irq(int irq, unsigned int cpu)
 	const struct cpumask *mask = cpumask_of(cpu);
 
 	spin_lock_irq(&desc->lock);
-	desc->affinity = *mask;
+	cpumask_copy(desc->affinity, mask);
 	desc->chip->set_affinity(irq, mask);
 	spin_unlock_irq(&desc->lock);
 }

arch/avr32/Kconfig

@@ -181,7 +181,7 @@ source "kernel/Kconfig.preempt"
 config QUICKLIST
 	def_bool y
 
-config HAVE_ARCH_BOOTMEM_NODE
+config HAVE_ARCH_BOOTMEM
 	def_bool n
 
 config ARCH_HAVE_MEMORY_PRESENT

arch/blackfin/include/asm/percpu.h

@@ -3,14 +3,4 @@
 
 #include <asm-generic/percpu.h>
 
-#ifdef CONFIG_MODULES
-#define PERCPU_MODULE_RESERVE 8192
-#else
-#define PERCPU_MODULE_RESERVE 0
-#endif
-
-#define PERCPU_ENOUGH_ROOM \
-	(ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \
-	 PERCPU_MODULE_RESERVE)
-
 #endif	/* __ARCH_BLACKFIN_PERCPU__ */

arch/blackfin/kernel/irqchip.c

@@ -70,6 +70,11 @@ static struct irq_desc bad_irq_desc = {
 #endif
 };
 
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* We are not allocating a variable-sized bad_irq_desc.affinity */
+#error "Blackfin architecture does not support CONFIG_CPUMASK_OFFSTACK."
+#endif
+
 int show_interrupts(struct seq_file *p, void *v)
 {
 	int i = *(loff_t *) v, j;

arch/ia64/include/asm/percpu.h

@@ -27,12 +27,12 @@ extern void *per_cpu_init(void);
 
 #else /* ! SMP */
 
-#define PER_CPU_ATTRIBUTES	__attribute__((__section__(".data.percpu")))
-
 #define per_cpu_init()				(__phys_per_cpu_start)
 
 #endif	/* SMP */
 
+#define PER_CPU_BASE_SECTION ".data.percpu"
+
 /*
  * Be extremely careful when taking the address of this variable!  Due to virtual
  * remapping, it is different from the canonical address returned by __get_cpu_var(var)!

arch/ia64/include/asm/topology.h

@@ -84,7 +84,7 @@ void build_cpu_to_node_map(void);
 	.child			= NULL,			\
 	.groups			= NULL,			\
 	.min_interval		= 8,			\
-	.max_interval		= 8*(min(num_online_cpus(), 32)), \
+	.max_interval		= 8*(min(num_online_cpus(), 32U)), \
 	.busy_factor		= 64,			\
 	.imbalance_pct		= 125,			\
 	.cache_nice_tries	= 2,			\

arch/ia64/include/asm/uv/uv.h

@@ -0,0 +1,13 @@
+#ifndef _ASM_IA64_UV_UV_H
+#define _ASM_IA64_UV_UV_H
+
+#include <asm/system.h>
+#include <asm/sn/simulator.h>
+
+static inline int is_uv_system(void)
+{
+	/* temporary support for running on hardware simulator */
+	return IS_MEDUSA() || ia64_platform_is("uv");
+}
+
+#endif	/* _ASM_IA64_UV_UV_H */

arch/ia64/kernel/acpi.c

@@ -199,6 +199,10 @@ char *__init __acpi_map_table(unsigned long phys_addr, unsigned long size)
 	return __va(phys_addr);
 }
 
+void __init __acpi_unmap_table(char *map, unsigned long size)
+{
+}
+
 /* --------------------------------------------------------------------------
                             Boot-time Table Parsing
    -------------------------------------------------------------------------- */

arch/ia64/kernel/iosapic.c

@@ -880,7 +880,7 @@ iosapic_unregister_intr (unsigned int gsi)
 	if (iosapic_intr_info[irq].count == 0) {
 #ifdef CONFIG_SMP
 		/* Clear affinity */
-		cpus_setall(idesc->affinity);
+		cpumask_setall(idesc->affinity);
 #endif
 		/* Clear the interrupt information */
 		iosapic_intr_info[irq].dest = 0;

arch/ia64/kernel/irq.c

@@ -103,7 +103,7 @@ static char irq_redir [NR_IRQS]; // = { [0 ... NR_IRQS-1] = 1 };
 void set_irq_affinity_info (unsigned int irq, int hwid, int redir)
 {
 	if (irq < NR_IRQS) {
-		cpumask_copy(&irq_desc[irq].affinity,
+		cpumask_copy(irq_desc[irq].affinity,
 			     cpumask_of(cpu_logical_id(hwid)));
 		irq_redir[irq] = (char) (redir & 0xff);
 	}
@@ -148,7 +148,7 @@ static void migrate_irqs(void)
 		if (desc->status == IRQ_PER_CPU)
 			continue;
 
-		if (cpumask_any_and(&irq_desc[irq].affinity, cpu_online_mask)
+		if (cpumask_any_and(irq_desc[irq].affinity, cpu_online_mask)
 		    >= nr_cpu_ids) {
 			/*
 			 * Save it for phase 2 processing

arch/ia64/kernel/irq_ia64.c

@@ -493,11 +493,13 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs)
 	saved_tpr = ia64_getreg(_IA64_REG_CR_TPR);
 	ia64_srlz_d();
 	while (vector != IA64_SPURIOUS_INT_VECTOR) {
+		struct irq_desc *desc = irq_to_desc(vector);
+
 		if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) {
 			smp_local_flush_tlb();
-			kstat_this_cpu.irqs[vector]++;
+			kstat_incr_irqs_this_cpu(vector, desc);
 		} else if (unlikely(IS_RESCHEDULE(vector)))
-			kstat_this_cpu.irqs[vector]++;
+			kstat_incr_irqs_this_cpu(vector, desc);
 		else {
 			int irq = local_vector_to_irq(vector);
 
@@ -551,11 +553,13 @@ void ia64_process_pending_intr(void)
 	  * Perform normal interrupt style processing
 	  */
 	while (vector != IA64_SPURIOUS_INT_VECTOR) {
+		struct irq_desc *desc = irq_to_desc(vector);
+
 		if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) {
 			smp_local_flush_tlb();
-			kstat_this_cpu.irqs[vector]++;
+			kstat_incr_irqs_this_cpu(vector, desc);
 		} else if (unlikely(IS_RESCHEDULE(vector)))
-			kstat_this_cpu.irqs[vector]++;
+			kstat_incr_irqs_this_cpu(vector, desc);
 		else {
 			struct pt_regs *old_regs = set_irq_regs(NULL);
 			int irq = local_vector_to_irq(vector);

arch/ia64/kernel/msi_ia64.c

@@ -38,7 +38,7 @@ static void ia64_set_msi_irq_affinity(unsigned int irq,
 	msg.data = data;
 
 	write_msi_msg(irq, &msg);
-	irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+	cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
 }
 #endif /* CONFIG_SMP */
 
@@ -150,7 +150,7 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID_CPU(cpu_physical_id(cpu));
 
 	dmar_msi_write(irq, &msg);
-	irq_desc[irq].affinity = *mask;
+	cpumask_copy(irq_desc[irq].affinity, mask);
 }
 #endif /* CONFIG_SMP */
 

arch/ia64/kernel/vmlinux.lds.S

@@ -213,16 +213,9 @@ SECTIONS
         { *(.data.cacheline_aligned) }
 
   /* Per-cpu data: */
-  percpu : { } :percpu
   . = ALIGN(PERCPU_PAGE_SIZE);
-  __phys_per_cpu_start = .;
-  .data.percpu PERCPU_ADDR : AT(__phys_per_cpu_start - LOAD_OFFSET)
-	{
-		__per_cpu_start = .;
-		*(.data.percpu)
-		*(.data.percpu.shared_aligned)
-		__per_cpu_end = .;
-	}
+  PERCPU_VADDR(PERCPU_ADDR, :percpu)
+  __phys_per_cpu_start = __per_cpu_load;
   . = __phys_per_cpu_start + PERCPU_PAGE_SIZE;	/* ensure percpu data fits
   						 * into percpu page size
 						 */

arch/ia64/sn/kernel/msi_sn.c

@@ -205,7 +205,7 @@ static void sn_set_msi_irq_affinity(unsigned int irq,
 	msg.address_lo = (u32)(bus_addr & 0x00000000ffffffff);
 
 	write_msi_msg(irq, &msg);
-	irq_desc[irq].affinity = *cpu_mask;
+	cpumask_copy(irq_desc[irq].affinity, cpu_mask);
 }
 #endif /* CONFIG_SMP */
 

arch/mips/include/asm/irq.h

@@ -66,7 +66,7 @@ extern void smtc_forward_irq(unsigned int irq);
  */
 #define IRQ_AFFINITY_HOOK(irq)						\
 do {									\
-    if (!cpu_isset(smp_processor_id(), irq_desc[irq].affinity)) {	\
+    if (!cpumask_test_cpu(smp_processor_id(), irq_desc[irq].affinity)) {\
 	smtc_forward_irq(irq);						\
 	irq_exit();							\
 	return;								\

arch/mips/kernel/irq-gic.c

@@ -187,7 +187,7 @@ static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 		set_bit(irq, pcpu_masks[first_cpu(tmp)].pcpu_mask);
 
 	}
-	irq_desc[irq].affinity = *cpumask;
+	cpumask_copy(irq_desc[irq].affinity, cpumask);
 	spin_unlock_irqrestore(&gic_lock, flags);
 
 }

arch/mips/kernel/smtc.c

@@ -686,7 +686,7 @@ void smtc_forward_irq(unsigned int irq)
 	 * and efficiency, we just pick the easiest one to find.
 	 */
 
-	target = first_cpu(irq_desc[irq].affinity);
+	target = cpumask_first(irq_desc[irq].affinity);
 
 	/*
 	 * We depend on the platform code to have correctly processed
@@ -921,11 +921,13 @@ void ipi_decode(struct smtc_ipi *pipi)
 	struct clock_event_device *cd;
 	void *arg_copy = pipi->arg;
 	int type_copy = pipi->type;
+	int irq = MIPS_CPU_IRQ_BASE + 1;
+
 	smtc_ipi_nq(&freeIPIq, pipi);
 	switch (type_copy) {
 	case SMTC_CLOCK_TICK:
 		irq_enter();
-		kstat_this_cpu.irqs[MIPS_CPU_IRQ_BASE + 1]++;
+		kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 		cd = &per_cpu(mips_clockevent_device, cpu);
 		cd->event_handler(cd);
 		irq_exit();

arch/mips/mti-malta/malta-smtc.c

@@ -116,7 +116,7 @@ struct plat_smp_ops msmtc_smp_ops = {
 
 void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 {
-	cpumask_t tmask = *affinity;
+	cpumask_t tmask;
 	int cpu = 0;
 	void smtc_set_irq_affinity(unsigned int irq, cpumask_t aff);
 
@@ -139,11 +139,12 @@ void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 	 * be made to forward to an offline "CPU".
 	 */
 
+	cpumask_copy(&tmask, affinity);
 	for_each_cpu(cpu, affinity) {
 		if ((cpu_data[cpu].vpe_id != 0) || !cpu_online(cpu))
 			cpu_clear(cpu, tmask);
 	}
-	irq_desc[irq].affinity = tmask;
+	cpumask_copy(irq_desc[irq].affinity, &tmask);
 
 	if (cpus_empty(tmask))
 		/*

arch/mips/sgi-ip22/ip22-int.c

@@ -155,7 +155,7 @@ static void indy_buserror_irq(void)
 	int irq = SGI_BUSERR_IRQ;
 
 	irq_enter();
-	kstat_this_cpu.irqs[irq]++;
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 	ip22_be_interrupt(irq);
 	irq_exit();
 }

arch/mips/sgi-ip22/ip22-time.c

@@ -122,7 +122,7 @@ void indy_8254timer_irq(void)
 	char c;
 
 	irq_enter();
-	kstat_this_cpu.irqs[irq]++;
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 	printk(KERN_ALERT "Oops, got 8254 interrupt.\n");
 	ArcRead(0, &c, 1, &cnt);
 	ArcEnterInteractiveMode();

arch/mips/sibyte/bcm1480/smp.c

@@ -178,9 +178,10 @@ struct plat_smp_ops bcm1480_smp_ops = {
 void bcm1480_mailbox_interrupt(void)
 {
 	int cpu = smp_processor_id();
+	int irq = K_BCM1480_INT_MBOX_0_0;
 	unsigned int action;
 
-	kstat_this_cpu.irqs[K_BCM1480_INT_MBOX_0_0]++;
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 	/* Load the mailbox register to figure out what we're supposed to do */
 	action = (__raw_readq(mailbox_0_regs[cpu]) >> 48) & 0xffff;
 

arch/mips/sibyte/sb1250/smp.c

@@ -166,9 +166,10 @@ struct plat_smp_ops sb_smp_ops = {
 void sb1250_mailbox_interrupt(void)
 {
 	int cpu = smp_processor_id();
+	int irq = K_INT_MBOX_0;
 	unsigned int action;
 
-	kstat_this_cpu.irqs[K_INT_MBOX_0]++;
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 	/* Load the mailbox register to figure out what we're supposed to do */
 	action = (____raw_readq(mailbox_regs[cpu]) >> 48) & 0xffff;
 

arch/mn10300/kernel/mn10300-watchdog.c

@@ -130,6 +130,7 @@ void watchdog_interrupt(struct pt_regs *regs, enum exception_code excep)
 	 * the stack NMI-atomically, it's safe to use smp_processor_id().
 	 */
 	int sum, cpu = smp_processor_id();
+	int irq = NMIIRQ;
 	u8 wdt, tmp;
 
 	wdt = WDCTR & ~WDCTR_WDCNE;
@@ -138,7 +139,7 @@ void watchdog_interrupt(struct pt_regs *regs, enum exception_code excep)
 	NMICR = NMICR_WDIF;
 
 	nmi_count(cpu)++;
-	kstat_this_cpu.irqs[NMIIRQ]++;
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 	sum = irq_stat[cpu].__irq_count;
 
 	if (last_irq_sums[cpu] == sum) {

arch/parisc/kernel/irq.c

@@ -138,7 +138,7 @@ static void cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest)
 	if (cpu_dest < 0)
 		return;
 
-	cpumask_copy(&irq_desc[irq].affinity, &cpumask_of_cpu(cpu_dest));
+	cpumask_copy(&irq_desc[irq].affinity, dest);
 }
 #endif
 

arch/powerpc/kernel/irq.c

@@ -231,7 +231,7 @@ void fixup_irqs(cpumask_t map)
 		if (irq_desc[irq].status & IRQ_PER_CPU)
 			continue;
 
-		cpus_and(mask, irq_desc[irq].affinity, map);
+		cpumask_and(&mask, irq_desc[irq].affinity, &map);
 		if (any_online_cpu(mask) == NR_CPUS) {
 			printk("Breaking affinity for irq %i\n", irq);
 			mask = map;

arch/powerpc/kernel/vmlinux.lds.S

@@ -181,13 +181,7 @@ SECTIONS
 		__initramfs_end = .;
 	}
 #endif
-	. = ALIGN(PAGE_SIZE);
-	.data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {
-		__per_cpu_start = .;
-		*(.data.percpu)
-		*(.data.percpu.shared_aligned)
-		__per_cpu_end = .;
-	}
+	PERCPU(PAGE_SIZE)
 
 	. = ALIGN(8);
 	.machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {

arch/powerpc/platforms/pseries/xics.c

@@ -153,9 +153,10 @@ static int get_irq_server(unsigned int virq, unsigned int strict_check)
 {
 	int server;
 	/* For the moment only implement delivery to all cpus or one cpu */
-	cpumask_t cpumask = irq_desc[virq].affinity;
+	cpumask_t cpumask;
 	cpumask_t tmp = CPU_MASK_NONE;
 
+	cpumask_copy(&cpumask, irq_desc[virq].affinity);
 	if (!distribute_irqs)
 		return default_server;
 
@@ -869,7 +870,7 @@ void xics_migrate_irqs_away(void)
 		       virq, cpu);
 
 		/* Reset affinity to all cpus */
-		irq_desc[virq].affinity = CPU_MASK_ALL;
+		cpumask_setall(irq_desc[virq].affinity);
 		desc->chip->set_affinity(virq, cpu_all_mask);
 unlock:
 		spin_unlock_irqrestore(&desc->lock, flags);

arch/powerpc/sysdev/mpic.c

@@ -566,9 +566,10 @@ static void __init mpic_scan_ht_pics(struct mpic *mpic)
 #ifdef CONFIG_SMP
 static int irq_choose_cpu(unsigned int virt_irq)
 {
-	cpumask_t mask = irq_desc[virt_irq].affinity;
+	cpumask_t mask;
 	int cpuid;
 
+	cpumask_copy(&mask, irq_desc[virt_irq].affinity);
 	if (cpus_equal(mask, CPU_MASK_ALL)) {
 		static int irq_rover;
 		static DEFINE_SPINLOCK(irq_rover_lock);

arch/sparc/kernel/irq_64.c

@@ -252,9 +252,10 @@ struct irq_handler_data {
 #ifdef CONFIG_SMP
 static int irq_choose_cpu(unsigned int virt_irq)
 {
-	cpumask_t mask = irq_desc[virt_irq].affinity;
+	cpumask_t mask;
 	int cpuid;
 
+	cpumask_copy(&mask, irq_desc[virt_irq].affinity);
 	if (cpus_equal(mask, CPU_MASK_ALL)) {
 		static int irq_rover;
 		static DEFINE_SPINLOCK(irq_rover_lock);
@@ -805,7 +806,7 @@ void fixup_irqs(void)
 		    !(irq_desc[irq].status & IRQ_PER_CPU)) {
 			if (irq_desc[irq].chip->set_affinity)
 				irq_desc[irq].chip->set_affinity(irq,
-					&irq_desc[irq].affinity);
+					irq_desc[irq].affinity);
 		}
 		spin_unlock_irqrestore(&irq_desc[irq].lock, flags);
 	}

arch/sparc/kernel/time_64.c

@@ -729,7 +729,7 @@ void timer_interrupt(int irq, struct pt_regs *regs)
 
 	irq_enter();
 
-	kstat_this_cpu.irqs[0]++;
+	kstat_incr_irqs_this_cpu(0, irq_to_desc(0));
 
 	if (unlikely(!evt->event_handler)) {
 		printk(KERN_WARNING

arch/x86/Kconfig.cpu

@@ -50,7 +50,7 @@ config M386
 config M486
 	bool "486"
 	depends on X86_32
-	help
+	---help---
 	  Select this for a 486 series processor, either Intel or one of the
 	  compatible processors from AMD, Cyrix, IBM, or Intel.  Includes DX,
 	  DX2, and DX4 variants; also SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or
@@ -59,7 +59,7 @@ config M486
 config M586
 	bool "586/K5/5x86/6x86/6x86MX"
 	depends on X86_32
-	help
+	---help---
 	  Select this for an 586 or 686 series processor such as the AMD K5,
 	  the Cyrix 5x86, 6x86 and 6x86MX.  This choice does not
 	  assume the RDTSC (Read Time Stamp Counter) instruction.
@@ -67,21 +67,21 @@ config M586
 config M586TSC
 	bool "Pentium-Classic"
 	depends on X86_32
-	help
+	---help---
 	  Select this for a Pentium Classic processor with the RDTSC (Read
 	  Time Stamp Counter) instruction for benchmarking.
 
 config M586MMX
 	bool "Pentium-MMX"
 	depends on X86_32
-	help
+	---help---
 	  Select this for a Pentium with the MMX graphics/multimedia
 	  extended instructions.
 
 config M686
 	bool "Pentium-Pro"
 	depends on X86_32
-	help
+	---help---
 	  Select this for Intel Pentium Pro chips.  This enables the use of
 	  Pentium Pro extended instructions, and disables the init-time guard
 	  against the f00f bug found in earlier Pentiums.
@@ -89,7 +89,7 @@ config M686
 config MPENTIUMII
 	bool "Pentium-II/Celeron(pre-Coppermine)"
 	depends on X86_32
-	help
+	---help---
 	  Select this for Intel chips based on the Pentium-II and
 	  pre-Coppermine Celeron core.  This option enables an unaligned
 	  copy optimization, compiles the kernel with optimization flags
@@ -99,7 +99,7 @@ config MPENTIUMII
 config MPENTIUMIII
 	bool "Pentium-III/Celeron(Coppermine)/Pentium-III Xeon"
 	depends on X86_32
-	help
+	---help---
 	  Select this for Intel chips based on the Pentium-III and
 	  Celeron-Coppermine core.  This option enables use of some
 	  extended prefetch instructions in addition to the Pentium II
@@ -108,14 +108,14 @@ config MPENTIUMIII
 config MPENTIUMM
 	bool "Pentium M"
 	depends on X86_32
-	help
+	---help---
 	  Select this for Intel Pentium M (not Pentium-4 M)
 	  notebook chips.
 
 config MPENTIUM4
 	bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon"
 	depends on X86_32
-	help
+	---help---
 	  Select this for Intel Pentium 4 chips.  This includes the
 	  Pentium 4, Pentium D, P4-based Celeron and Xeon, and
 	  Pentium-4 M (not Pentium M) chips.  This option enables compile
@@ -151,7 +151,7 @@ config MPENTIUM4
 config MK6
 	bool "K6/K6-II/K6-III"
 	depends on X86_32
-	help
+	---help---
 	  Select this for an AMD K6-family processor.  Enables use of
 	  some extended instructions, and passes appropriate optimization
 	  flags to GCC.
@@ -159,14 +159,14 @@ config MK6
 config MK7
 	bool "Athlon/Duron/K7"
 	depends on X86_32
-	help
+	---help---
 	  Select this for an AMD Athlon K7-family processor.  Enables use of
 	  some extended instructions, and passes appropriate optimization
 	  flags to GCC.
 
 config MK8
 	bool "Opteron/Athlon64/Hammer/K8"
-	help
+	---help---
 	  Select this for an AMD Opteron or Athlon64 Hammer-family processor.
 	  Enables use of some extended instructions, and passes appropriate
 	  optimization flags to GCC.
@@ -174,7 +174,7 @@ config MK8
 config MCRUSOE
 	bool "Crusoe"
 	depends on X86_32
-	help
+	---help---
 	  Select this for a Transmeta Crusoe processor.  Treats the processor
 	  like a 586 with TSC, and sets some GCC optimization flags (like a
 	  Pentium Pro with no alignment requirements).
@@ -182,13 +182,13 @@ config MCRUSOE
 config MEFFICEON
 	bool "Efficeon"
 	depends on X86_32
-	help
+	---help---
 	  Select this for a Transmeta Efficeon processor.
 
 config MWINCHIPC6
 	bool "Winchip-C6"
 	depends on X86_32
-	help
+	---help---
 	  Select this for an IDT Winchip C6 chip.  Linux and GCC
 	  treat this chip as a 586TSC with some extended instructions
 	  and alignment requirements.
@@ -196,7 +196,7 @@ config MWINCHIPC6
 config MWINCHIP3D
 	bool "Winchip-2/Winchip-2A/Winchip-3"
 	depends on X86_32
-	help
+	---help---
 	  Select this for an IDT Winchip-2, 2A or 3.  Linux and GCC
 	  treat this chip as a 586TSC with some extended instructions
 	  and alignment requirements.  Also enable out of order memory
@@ -206,19 +206,19 @@ config MWINCHIP3D
 config MGEODEGX1
 	bool "GeodeGX1"
 	depends on X86_32
-	help
+	---help---
 	  Select this for a Geode GX1 (Cyrix MediaGX) chip.
 
 config MGEODE_LX
 	bool "Geode GX/LX"
 	depends on X86_32
-	help
+	---help---
 	  Select this for AMD Geode GX and LX processors.
 
 config MCYRIXIII
 	bool "CyrixIII/VIA-C3"
 	depends on X86_32
-	help
+	---help---
 	  Select this for a Cyrix III or C3 chip.  Presently Linux and GCC
 	  treat this chip as a generic 586. Whilst the CPU is 686 class,
 	  it lacks the cmov extension which gcc assumes is present when
@@ -230,7 +230,7 @@ config MCYRIXIII
 config MVIAC3_2
 	bool "VIA C3-2 (Nehemiah)"
 	depends on X86_32
-	help
+	---help---
 	  Select this for a VIA C3 "Nehemiah". Selecting this enables usage
 	  of SSE and tells gcc to treat the CPU as a 686.
 	  Note, this kernel will not boot on older (pre model 9) C3s.
@@ -238,14 +238,14 @@ config MVIAC3_2
 config MVIAC7
 	bool "VIA C7"
 	depends on X86_32
-	help
+	---help---
 	  Select this for a VIA C7.  Selecting this uses the correct cache
 	  shift and tells gcc to treat the CPU as a 686.
 
 config MPSC
 	bool "Intel P4 / older Netburst based Xeon"
 	depends on X86_64
-	help
+	---help---
 	  Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey
 	  Xeon CPUs with Intel 64bit which is compatible with x86-64.
 	  Note that the latest Xeons (Xeon 51xx and 53xx) are not based on the
@@ -255,7 +255,7 @@ config MPSC
 
 config MCORE2
 	bool "Core 2/newer Xeon"
-	help
+	---help---
 
 	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and
 	  53xx) CPUs. You can distinguish newer from older Xeons by the CPU
@@ -265,7 +265,7 @@ config MCORE2
 config GENERIC_CPU
 	bool "Generic-x86-64"
 	depends on X86_64
-	help
+	---help---
 	  Generic x86-64 CPU.
 	  Run equally well on all x86-64 CPUs.
 
@@ -274,7 +274,7 @@ endchoice
 config X86_GENERIC
 	bool "Generic x86 support"
 	depends on X86_32
-	help
+	---help---
 	  Instead of just including optimizations for the selected
 	  x86 variant (e.g. PII, Crusoe or Athlon), include some more
 	  generic optimizations as well. This will make the kernel
@@ -294,25 +294,23 @@ config X86_CPU
 # Define implied options from the CPU selection here
 config X86_L1_CACHE_BYTES
 	int
-	default "128" if GENERIC_CPU || MPSC
-	default "64" if MK8 || MCORE2
-	depends on X86_64
+	default "128" if MPSC
+	default "64" if GENERIC_CPU || MK8 || MCORE2 || X86_32
 
 config X86_INTERNODE_CACHE_BYTES
 	int
 	default "4096" if X86_VSMP
 	default X86_L1_CACHE_BYTES if !X86_VSMP
-	depends on X86_64
 
 config X86_CMPXCHG
 	def_bool X86_64 || (X86_32 && !M386)
 
 config X86_L1_CACHE_SHIFT
 	int
-	default "7" if MPENTIUM4 || X86_GENERIC || GENERIC_CPU || MPSC
+	default "7" if MPENTIUM4 || MPSC
 	default "4" if X86_ELAN || M486 || M386 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
-	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7
+	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7 || X86_GENERIC || GENERIC_CPU
 
 config X86_XADD
 	def_bool y
@@ -321,7 +319,7 @@ config X86_XADD
 config X86_PPRO_FENCE
 	bool "PentiumPro memory ordering errata workaround"
 	depends on M686 || M586MMX || M586TSC || M586 || M486 || M386 || MGEODEGX1
-	help
+	---help---
 	  Old PentiumPro multiprocessor systems had errata that could cause
 	  memory operations to violate the x86 ordering standard in rare cases.
 	  Enabling this option will attempt to work around some (but not all)
@@ -414,14 +412,14 @@ config X86_DEBUGCTLMSR
 
 menuconfig PROCESSOR_SELECT
 	bool "Supported processor vendors" if EMBEDDED
-	help
+	---help---
 	  This lets you choose what x86 vendor support code your kernel
 	  will include.
 
 config CPU_SUP_INTEL
 	default y
 	bool "Support Intel processors" if PROCESSOR_SELECT
-	help
+	---help---
 	  This enables detection, tunings and quirks for Intel processors
 
 	  You need this enabled if you want your kernel to run on an
@@ -435,7 +433,7 @@ config CPU_SUP_CYRIX_32
 	default y
 	bool "Support Cyrix processors" if PROCESSOR_SELECT
 	depends on !64BIT
-	help
+	---help---
 	  This enables detection, tunings and quirks for Cyrix processors
 
 	  You need this enabled if you want your kernel to run on a
@@ -448,7 +446,7 @@ config CPU_SUP_CYRIX_32
 config CPU_SUP_AMD
 	default y
 	bool "Support AMD processors" if PROCESSOR_SELECT
-	help
+	---help---
 	  This enables detection, tunings and quirks for AMD processors
 
 	  You need this enabled if you want your kernel to run on an
@@ -462,7 +460,7 @@ config CPU_SUP_CENTAUR_32
 	default y
 	bool "Support Centaur processors" if PROCESSOR_SELECT
 	depends on !64BIT
-	help
+	---help---
 	  This enables detection, tunings and quirks for Centaur processors
 
 	  You need this enabled if you want your kernel to run on a
@@ -476,7 +474,7 @@ config CPU_SUP_CENTAUR_64
 	default y
 	bool "Support Centaur processors" if PROCESSOR_SELECT
 	depends on 64BIT
-	help
+	---help---
 	  This enables detection, tunings and quirks for Centaur processors
 
 	  You need this enabled if you want your kernel to run on a
@@ -490,7 +488,7 @@ config CPU_SUP_TRANSMETA_32
 	default y
 	bool "Support Transmeta processors" if PROCESSOR_SELECT
 	depends on !64BIT
-	help
+	---help---
 	  This enables detection, tunings and quirks for Transmeta processors
 
 	  You need this enabled if you want your kernel to run on a
@@ -504,7 +502,7 @@ config CPU_SUP_UMC_32
 	default y
 	bool "Support UMC processors" if PROCESSOR_SELECT
 	depends on !64BIT
-	help
+	---help---
 	  This enables detection, tunings and quirks for UMC processors
 
 	  You need this enabled if you want your kernel to run on a
@@ -523,7 +521,7 @@ config X86_PTRACE_BTS
 	bool "Branch Trace Store"
 	default y
 	depends on X86_DEBUGCTLMSR
-	help
+	---help---
 	  This adds a ptrace interface to the hardware's branch trace store.
 
 	  Debuggers may use it to collect an execution trace of the debugged

arch/x86/Kconfig.debug

@@ -7,7 +7,7 @@ source "lib/Kconfig.debug"
 
 config STRICT_DEVMEM
 	bool "Filter access to /dev/mem"
-	help
+	---help---
 	  If this option is disabled, you allow userspace (root) access to all
 	  of memory, including kernel and userspace memory. Accidental
 	  access to this is obviously disastrous, but specific access can
@@ -25,7 +25,7 @@ config STRICT_DEVMEM
 config X86_VERBOSE_BOOTUP
 	bool "Enable verbose x86 bootup info messages"
 	default y
-	help
+	---help---
 	  Enables the informational output from the decompression stage
 	  (e.g. bzImage) of the boot. If you disable this you will still
 	  see errors. Disable this if you want silent bootup.
@@ -33,7 +33,7 @@ config X86_VERBOSE_BOOTUP
 config EARLY_PRINTK
 	bool "Early printk" if EMBEDDED
 	default y
-	help
+	---help---
 	  Write kernel log output directly into the VGA buffer or to a serial
 	  port.
 
@@ -47,7 +47,7 @@ config EARLY_PRINTK_DBGP
 	bool "Early printk via EHCI debug port"
 	default n
 	depends on EARLY_PRINTK && PCI
-	help
+	---help---
 	  Write kernel log output directly into the EHCI debug port.
 
 	  This is useful for kernel debugging when your machine crashes very
@@ -59,14 +59,14 @@ config EARLY_PRINTK_DBGP
 config DEBUG_STACKOVERFLOW
 	bool "Check for stack overflows"
 	depends on DEBUG_KERNEL
-	help
+	---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
+	---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.
 
@@ -75,7 +75,7 @@ config DEBUG_STACK_USAGE
 config DEBUG_PAGEALLOC
 	bool "Debug page memory allocations"
 	depends on DEBUG_KERNEL
-	help
+	---help---
 	  Unmap pages from the kernel linear mapping after free_pages().
 	  This results in a large slowdown, but helps to find certain types
 	  of memory corruptions.
@@ -83,9 +83,9 @@ config DEBUG_PAGEALLOC
 config DEBUG_PER_CPU_MAPS
 	bool "Debug access to per_cpu maps"
 	depends on DEBUG_KERNEL
-	depends on X86_SMP
+	depends on SMP
 	default n
-	help
+	---help---
 	  Say Y to verify that the per_cpu map being accessed has
 	  been setup.  Adds a fair amount of code to kernel memory
 	  and decreases performance.
@@ -96,7 +96,7 @@ config X86_PTDUMP
 	bool "Export kernel pagetable layout to userspace via debugfs"
 	depends on DEBUG_KERNEL
 	select DEBUG_FS
-	help
+	---help---
 	  Say Y here if you want to show the kernel pagetable layout in a
 	  debugfs file. This information is only useful for kernel developers
 	  who are working in architecture specific areas of the kernel.
@@ -108,7 +108,7 @@ config DEBUG_RODATA
 	bool "Write protect kernel read-only data structures"
 	default y
 	depends on DEBUG_KERNEL
-	help
+	---help---
 	  Mark the kernel read-only data as write-protected in the pagetables,
 	  in order to catch accidental (and incorrect) writes to such const
 	  data. This is recommended so that we can catch kernel bugs sooner.
@@ -117,7 +117,8 @@ config DEBUG_RODATA
 config DEBUG_RODATA_TEST
 	bool "Testcase for the DEBUG_RODATA feature"
 	depends on DEBUG_RODATA
-	help
+	default y
+	---help---
 	  This option enables a testcase for the DEBUG_RODATA
 	  feature as well as for the change_page_attr() infrastructure.
 	  If in doubt, say "N"
@@ -125,7 +126,7 @@ config DEBUG_RODATA_TEST
 config DEBUG_NX_TEST
 	tristate "Testcase for the NX non-executable stack feature"
 	depends on DEBUG_KERNEL && m
-	help
+	---help---
 	  This option enables a testcase for the CPU NX capability
 	  and the software setup of this feature.
 	  If in doubt, say "N"
@@ -133,7 +134,7 @@ config DEBUG_NX_TEST
 config 4KSTACKS
 	bool "Use 4Kb for kernel stacks instead of 8Kb"
 	depends on X86_32
-	help
+	---help---
 	  If you say Y here the kernel will use a 4Kb stacksize for the
 	  kernel stack attached to each process/thread. This facilitates
 	  running more threads on a system and also reduces the pressure
@@ -144,7 +145,7 @@ config DOUBLEFAULT
 	default y
 	bool "Enable doublefault exception handler" if EMBEDDED
 	depends on X86_32
-	help
+	---help---
 	  This option allows trapping of rare doublefault exceptions that
 	  would otherwise cause a system to silently reboot. Disabling this
 	  option saves about 4k and might cause you much additional grey
@@ -154,7 +155,7 @@ config IOMMU_DEBUG
 	bool "Enable IOMMU debugging"
 	depends on GART_IOMMU && DEBUG_KERNEL
 	depends on X86_64
-	help
+	---help---
 	  Force the IOMMU to on even when you have less than 4GB of
 	  memory and add debugging code. On overflow always panic. And
 	  allow to enable IOMMU leak tracing. Can be disabled at boot
@@ -170,7 +171,7 @@ config IOMMU_LEAK
 	bool "IOMMU leak tracing"
 	depends on DEBUG_KERNEL
 	depends on IOMMU_DEBUG
-	help
+	---help---
 	  Add a simple leak tracer to the IOMMU code. This is useful when you
 	  are debugging a buggy device driver that leaks IOMMU mappings.
 
@@ -203,25 +204,25 @@ choice
 
 config IO_DELAY_0X80
 	bool "port 0x80 based port-IO delay [recommended]"
-	help
+	---help---
 	  This is the traditional Linux IO delay used for in/out_p.
 	  It is the most tested hence safest selection here.
 
 config IO_DELAY_0XED
 	bool "port 0xed based port-IO delay"
-	help
+	---help---
 	  Use port 0xed as the IO delay. This frees up port 0x80 which is
 	  often used as a hardware-debug port.
 
 config IO_DELAY_UDELAY
 	bool "udelay based port-IO delay"
-	help
+	---help---
 	  Use udelay(2) as the IO delay method. This provides the delay
 	  while not having any side-effect on the IO port space.
 
 config IO_DELAY_NONE
 	bool "no port-IO delay"
-	help
+	---help---
 	  No port-IO delay. Will break on old boxes that require port-IO
 	  delay for certain operations. Should work on most new machines.
 
@@ -255,18 +256,18 @@ config DEBUG_BOOT_PARAMS
 	bool "Debug boot parameters"
 	depends on DEBUG_KERNEL
 	depends on DEBUG_FS
-	help
+	---help---
 	  This option will cause struct boot_params to be exported via debugfs.
 
 config CPA_DEBUG
 	bool "CPA self-test code"
 	depends on DEBUG_KERNEL
-	help
+	---help---
 	  Do change_page_attr() self-tests every 30 seconds.
 
 config OPTIMIZE_INLINING
 	bool "Allow gcc to uninline functions marked 'inline'"
-	help
+	---help---
 	  This option determines if the kernel forces gcc to inline the functions
 	  developers have marked 'inline'. Doing so takes away freedom from gcc to
 	  do what it thinks is best, which is desirable for the gcc 3.x series of
@@ -279,4 +280,3 @@ config OPTIMIZE_INLINING
 	  If unsure, say N.
 
 endmenu
-

arch/x86/Makefile

@@ -70,14 +70,17 @@ else
         # this works around some issues with generating unwind tables in older gccs
         # newer gccs do it by default
         KBUILD_CFLAGS += -maccumulate-outgoing-args
+endif
 
-        stackp := $(CONFIG_SHELL) $(srctree)/scripts/gcc-x86_64-has-stack-protector.sh
-        stackp-$(CONFIG_CC_STACKPROTECTOR) := $(shell $(stackp) \
-                "$(CC)" -fstack-protector )
-        stackp-$(CONFIG_CC_STACKPROTECTOR_ALL) += $(shell $(stackp) \
-                "$(CC)" -fstack-protector-all )
-
-        KBUILD_CFLAGS += $(stackp-y)
+ifdef CONFIG_CC_STACKPROTECTOR
+	cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh
+        ifeq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC)),y)
+                stackp-y := -fstack-protector
+                stackp-$(CONFIG_CC_STACKPROTECTOR_ALL) += -fstack-protector-all
+                KBUILD_CFLAGS += $(stackp-y)
+        else
+                $(warning stack protector enabled but no compiler support)
+        endif
 endif
 
 # Stackpointer is addressed different for 32 bit and 64 bit x86
@@ -102,29 +105,6 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 # prevent gcc from generating any FP code by mistake
 KBUILD_CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,)
 
-###
-# Sub architecture support
-# fcore-y is linked before mcore-y files.
-
-# Default subarch .c files
-mcore-y  := arch/x86/mach-default/
-
-# Voyager subarch support
-mflags-$(CONFIG_X86_VOYAGER)	:= -Iarch/x86/include/asm/mach-voyager
-mcore-$(CONFIG_X86_VOYAGER)	:= arch/x86/mach-voyager/
-
-# generic subarchitecture
-mflags-$(CONFIG_X86_GENERICARCH):= -Iarch/x86/include/asm/mach-generic
-fcore-$(CONFIG_X86_GENERICARCH)	+= arch/x86/mach-generic/
-mcore-$(CONFIG_X86_GENERICARCH)	:= arch/x86/mach-default/
-
-# default subarch .h files
-mflags-y += -Iarch/x86/include/asm/mach-default
-
-# 64 bit does not support subarch support - clear sub arch variables
-fcore-$(CONFIG_X86_64)  :=
-mcore-$(CONFIG_X86_64)  :=
-
 KBUILD_CFLAGS += $(mflags-y)
 KBUILD_AFLAGS += $(mflags-y)
 
@@ -150,9 +130,6 @@ core-$(CONFIG_LGUEST_GUEST) += arch/x86/lguest/
 core-y += arch/x86/kernel/
 core-y += arch/x86/mm/
 
-# Remaining sub architecture files
-core-y += $(mcore-y)
-
 core-y += arch/x86/crypto/
 core-y += arch/x86/vdso/
 core-$(CONFIG_IA32_EMULATION) += arch/x86/ia32/

arch/x86/boot/Makefile

@@ -32,7 +32,6 @@ setup-y		+= a20.o cmdline.o copy.o cpu.o cpucheck.o edd.o
 setup-y		+= header.o main.o mca.o memory.o pm.o pmjump.o
 setup-y		+= printf.o string.o tty.o video.o video-mode.o version.o
 setup-$(CONFIG_X86_APM_BOOT) += apm.o
-setup-$(CONFIG_X86_VOYAGER) += voyager.o
 
 # The link order of the video-*.o modules can matter.  In particular,
 # video-vga.o *must* be listed first, followed by video-vesa.o.

arch/x86/boot/a20.c

@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007-2008 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -15,16 +16,23 @@
 #include "boot.h"
 
 #define MAX_8042_LOOPS	100000
+#define MAX_8042_FF	32
 
 static int empty_8042(void)
 {
 	u8 status;
 	int loops = MAX_8042_LOOPS;
+	int ffs   = MAX_8042_FF;
 
 	while (loops--) {
 		io_delay();
 
 		status = inb(0x64);
+		if (status == 0xff) {
+			/* FF is a plausible, but very unlikely status */
+			if (!--ffs)
+				return -1; /* Assume no KBC present */
+		}
 		if (status & 1) {
 			/* Read and discard input data */
 			io_delay();
@@ -118,44 +126,37 @@ static void enable_a20_fast(void)
 
 int enable_a20(void)
 {
-#if defined(CONFIG_X86_ELAN)
-	/* Elan croaks if we try to touch the KBC */
-	enable_a20_fast();
-	while (!a20_test_long())
-		;
-	return 0;
-#elif defined(CONFIG_X86_VOYAGER)
-	/* On Voyager, a20_test() is unsafe? */
-	enable_a20_kbc();
-	return 0;
-#else
        int loops = A20_ENABLE_LOOPS;
-	while (loops--) {
-		/* First, check to see if A20 is already enabled
-		   (legacy free, etc.) */
-		if (a20_test_short())
-			return 0;
-
-		/* Next, try the BIOS (INT 0x15, AX=0x2401) */
-		enable_a20_bios();
-		if (a20_test_short())
-			return 0;
-
-		/* Try enabling A20 through the keyboard controller */
-		empty_8042();
-		if (a20_test_short())
-			return 0; /* BIOS worked, but with delayed reaction */
-
-		enable_a20_kbc();
-		if (a20_test_long())
-			return 0;
-
-		/* Finally, try enabling the "fast A20 gate" */
-		enable_a20_fast();
-		if (a20_test_long())
-			return 0;
-	}
-
-	return -1;
-#endif
+       int kbc_err;
+
+       while (loops--) {
+	       /* First, check to see if A20 is already enabled
+		  (legacy free, etc.) */
+	       if (a20_test_short())
+		       return 0;
+	       
+	       /* Next, try the BIOS (INT 0x15, AX=0x2401) */
+	       enable_a20_bios();
+	       if (a20_test_short())
+		       return 0;
+	       
+	       /* Try enabling A20 through the keyboard controller */
+	       kbc_err = empty_8042();
+
+	       if (a20_test_short())
+		       return 0; /* BIOS worked, but with delayed reaction */
+	
+	       if (!kbc_err) {
+		       enable_a20_kbc();
+		       if (a20_test_long())
+			       return 0;
+	       }
+	       
+	       /* Finally, try enabling the "fast A20 gate" */
+	       enable_a20_fast();
+	       if (a20_test_long())
+		       return 0;
+       }
+       
+       return -1;
 }

arch/x86/boot/boot.h

@@ -302,9 +302,6 @@ void probe_cards(int unsafe);
 /* video-vesa.c */
 void vesa_store_edid(void);
 
-/* voyager.c */
-int query_voyager(void);
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* BOOT_BOOT_H */

arch/x86/boot/compressed/Makefile

@@ -4,7 +4,7 @@
 # create a compressed vmlinux image from the original vmlinux
 #
 
-targets := vmlinux vmlinux.bin vmlinux.bin.gz head_$(BITS).o misc.o piggy.o
+targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma head_$(BITS).o misc.o piggy.o
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
@@ -47,18 +47,35 @@ ifeq ($(CONFIG_X86_32),y)
 ifdef CONFIG_RELOCATABLE
 $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin.all FORCE
 	$(call if_changed,gzip)
+$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin.all FORCE
+	$(call if_changed,bzip2)
+$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin.all FORCE
+	$(call if_changed,lzma)
 else
 $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,gzip)
+$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,bzip2)
+$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,lzma)
 endif
 LDFLAGS_piggy.o := -r --format binary --oformat elf32-i386 -T
 
 else
+
 $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,gzip)
+$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,bzip2)
+$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,lzma)
 
 LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T
 endif
 
-$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.gz FORCE
+suffix_$(CONFIG_KERNEL_GZIP)  = gz
+suffix_$(CONFIG_KERNEL_BZIP2) = bz2
+suffix_$(CONFIG_KERNEL_LZMA)  = lzma
+
+$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix_y) FORCE
 	$(call if_changed,ld)

arch/x86/boot/compressed/head_32.S

@@ -25,14 +25,12 @@
 
 #include <linux/linkage.h>
 #include <asm/segment.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
 #include <asm/boot.h>
 #include <asm/asm-offsets.h>
 
 .section ".text.head","ax",@progbits
-	.globl startup_32
-
-startup_32:
+ENTRY(startup_32)
 	cld
 	/* test KEEP_SEGMENTS flag to see if the bootloader is asking
 	 * us to not reload segments */
@@ -113,6 +111,8 @@ startup_32:
  */
 	leal relocated(%ebx), %eax
 	jmp *%eax
+ENDPROC(startup_32)
+
 .section ".text"
 relocated:
 

arch/x86/boot/compressed/head_64.S

@@ -26,8 +26,8 @@
 
 #include <linux/linkage.h>
 #include <asm/segment.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
+#include <asm/pgtable_types.h>
+#include <asm/page_types.h>
 #include <asm/boot.h>
 #include <asm/msr.h>
 #include <asm/processor-flags.h>
@@ -35,9 +35,7 @@
 
 .section ".text.head"
 	.code32
-	.globl startup_32
-
-startup_32:
+ENTRY(startup_32)
 	cld
 	/* test KEEP_SEGMENTS flag to see if the bootloader is asking
 	 * us to not reload segments */
@@ -176,6 +174,7 @@ startup_32:
 
 	/* Jump from 32bit compatibility mode into 64bit mode. */
 	lret
+ENDPROC(startup_32)
 
 no_longmode:
 	/* This isn't an x86-64 CPU so hang */
@@ -295,7 +294,6 @@ relocated:
 	call	decompress_kernel
 	popq	%rsi
 
-
 /*
  * Jump to the decompressed kernel.
  */

arch/x86/boot/compressed/misc.c

@@ -116,71 +116,13 @@
 /*
  * gzip declarations
  */
-
-#define OF(args)	args
 #define STATIC		static
 
 #undef memset
 #undef memcpy
 #define memzero(s, n)	memset((s), 0, (n))
 
-typedef unsigned char	uch;
-typedef unsigned short	ush;
-typedef unsigned long	ulg;
-
-/*
- * Window size must be at least 32k, and a power of two.
- * We don't actually have a window just a huge output buffer,
- * so we report a 2G window size, as that should always be
- * larger than our output buffer:
- */
-#define WSIZE		0x80000000
-
-/* Input buffer: */
-static unsigned char	*inbuf;
-
-/* Sliding window buffer (and final output buffer): */
-static unsigned char	*window;
-
-/* Valid bytes in inbuf: */
-static unsigned		insize;
-
-/* Index of next byte to be processed in inbuf: */
-static unsigned		inptr;
-
-/* Bytes in output buffer: */
-static unsigned		outcnt;
-
-/* gzip flag byte */
-#define ASCII_FLAG	0x01 /* bit 0 set: file probably ASCII text */
-#define CONTINUATION	0x02 /* bit 1 set: continuation of multi-part gz file */
-#define EXTRA_FIELD	0x04 /* bit 2 set: extra field present */
-#define ORIG_NAM	0x08 /* bit 3 set: original file name present */
-#define COMMENT		0x10 /* bit 4 set: file comment present */
-#define ENCRYPTED	0x20 /* bit 5 set: file is encrypted */
-#define RESERVED	0xC0 /* bit 6, 7:  reserved */
-
-#define get_byte()	(inptr < insize ? inbuf[inptr++] : fill_inbuf())
-
-/* Diagnostic functions */
-#ifdef DEBUG
-#  define Assert(cond, msg) do { if (!(cond)) error(msg); } while (0)
-#  define Trace(x)	do { fprintf x; } while (0)
-#  define Tracev(x)	do { if (verbose) fprintf x ; } while (0)
-#  define Tracevv(x)	do { if (verbose > 1) fprintf x ; } while (0)
-#  define Tracec(c, x)	do { if (verbose && (c)) fprintf x ; } while (0)
-#  define Tracecv(c, x)	do { if (verbose > 1 && (c)) fprintf x ; } while (0)
-#else
-#  define Assert(cond, msg)
-#  define Trace(x)
-#  define Tracev(x)
-#  define Tracevv(x)
-#  define Tracec(c, x)
-#  define Tracecv(c, x)
-#endif
 
-static int  fill_inbuf(void);
-static void flush_window(void);
 static void error(char *m);
 
 /*
@@ -189,13 +131,8 @@ static void error(char *m);
 static struct boot_params *real_mode;		/* Pointer to real-mode data */
 static int quiet;
 
-extern unsigned char input_data[];
-extern int input_len;
-
-static long bytes_out;
-
 static void *memset(void *s, int c, unsigned n);
-static void *memcpy(void *dest, const void *src, unsigned n);
+void *memcpy(void *dest, const void *src, unsigned n);
 
 static void __putstr(int, const char *);
 #define putstr(__x)  __putstr(0, __x)
@@ -213,7 +150,17 @@ static char *vidmem;
 static int vidport;
 static int lines, cols;
 
-#include "../../../../lib/inflate.c"
+#ifdef CONFIG_KERNEL_GZIP
+#include "../../../../lib/decompress_inflate.c"
+#endif
+
+#ifdef CONFIG_KERNEL_BZIP2
+#include "../../../../lib/decompress_bunzip2.c"
+#endif
+
+#ifdef CONFIG_KERNEL_LZMA
+#include "../../../../lib/decompress_unlzma.c"
+#endif
 
 static void scroll(void)
 {
@@ -282,7 +229,7 @@ static void *memset(void *s, int c, unsigned n)
 	return s;
 }
 
-static void *memcpy(void *dest, const void *src, unsigned n)
+void *memcpy(void *dest, const void *src, unsigned n)
 {
 	int i;
 	const char *s = src;
@@ -293,38 +240,6 @@ static void *memcpy(void *dest, const void *src, unsigned n)
 	return dest;
 }
 
-/* ===========================================================================
- * Fill the input buffer. This is called only when the buffer is empty
- * and at least one byte is really needed.
- */
-static int fill_inbuf(void)
-{
-	error("ran out of input data");
-	return 0;
-}
-
-/* ===========================================================================
- * Write the output window window[0..outcnt-1] and update crc and bytes_out.
- * (Used for the decompressed data only.)
- */
-static void flush_window(void)
-{
-	/* With my window equal to my output buffer
-	 * I only need to compute the crc here.
-	 */
-	unsigned long c = crc;         /* temporary variable */
-	unsigned n;
-	unsigned char *in, ch;
-
-	in = window;
-	for (n = 0; n < outcnt; n++) {
-		ch = *in++;
-		c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8);
-	}
-	crc = c;
-	bytes_out += (unsigned long)outcnt;
-	outcnt = 0;
-}
 
 static void error(char *x)
 {
@@ -407,12 +322,8 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	lines = real_mode->screen_info.orig_video_lines;
 	cols = real_mode->screen_info.orig_video_cols;
 
-	window = output;		/* Output buffer (Normally at 1M) */
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
-	inbuf  = input_data;		/* Input buffer */
-	insize = input_len;
-	inptr  = 0;
 
 #ifdef CONFIG_X86_64
 	if ((unsigned long)output & (__KERNEL_ALIGN - 1))
@@ -430,10 +341,9 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 #endif
 #endif
 
-	makecrc();
 	if (!quiet)
 		putstr("\nDecompressing Linux... ");
-	gunzip();
+	decompress(input_data, input_len, NULL, NULL, output, NULL, error);
 	parse_elf(output);
 	if (!quiet)
 		putstr("done.\nBooting the kernel.\n");

arch/x86/boot/copy.S

@@ -8,6 +8,8 @@
  *
  * ----------------------------------------------------------------------- */
 
+#include <linux/linkage.h>
+
 /*
  * Memory copy routines
  */
@@ -15,9 +17,7 @@
 	.code16gcc
 	.text
 
-	.globl	memcpy
-	.type	memcpy, @function
-memcpy:
+GLOBAL(memcpy)
 	pushw	%si
 	pushw	%di
 	movw	%ax, %di
@@ -31,11 +31,9 @@ memcpy:
 	popw	%di
 	popw	%si
 	ret
-	.size	memcpy, .-memcpy
+ENDPROC(memcpy)
 
-	.globl	memset
-	.type	memset, @function
-memset:
+GLOBAL(memset)
 	pushw	%di
 	movw	%ax, %di
 	movzbl	%dl, %eax
@@ -48,52 +46,42 @@ memset:
 	rep; stosb
 	popw	%di
 	ret
-	.size	memset, .-memset
+ENDPROC(memset)
 
-	.globl	copy_from_fs
-	.type	copy_from_fs, @function
-copy_from_fs:
+GLOBAL(copy_from_fs)
 	pushw	%ds
 	pushw	%fs
 	popw	%ds
 	call	memcpy
 	popw	%ds
 	ret
-	.size	copy_from_fs, .-copy_from_fs
+ENDPROC(copy_from_fs)
 
-	.globl	copy_to_fs
-	.type	copy_to_fs, @function
-copy_to_fs:
+GLOBAL(copy_to_fs)
 	pushw	%es
 	pushw	%fs
 	popw	%es
 	call	memcpy
 	popw	%es
 	ret
-	.size	copy_to_fs, .-copy_to_fs
+ENDPROC(copy_to_fs)
 
 #if 0 /* Not currently used, but can be enabled as needed */
-
-	.globl	copy_from_gs
-	.type	copy_from_gs, @function
-copy_from_gs:
+GLOBAL(copy_from_gs)
 	pushw	%ds
 	pushw	%gs
 	popw	%ds
 	call	memcpy
 	popw	%ds
 	ret
-	.size	copy_from_gs, .-copy_from_gs
-	.globl	copy_to_gs
+ENDPROC(copy_from_gs)
 
-	.type	copy_to_gs, @function
-copy_to_gs:
+GLOBAL(copy_to_gs)
 	pushw	%es
 	pushw	%gs
 	popw	%es
 	call	memcpy
 	popw	%es
 	ret
-	.size	copy_to_gs, .-copy_to_gs
-
+ENDPROC(copy_to_gs)
 #endif

arch/x86/boot/header.S

@@ -19,7 +19,7 @@
 #include <linux/utsrelease.h>
 #include <asm/boot.h>
 #include <asm/e820.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
 #include <asm/setup.h>
 #include "boot.h"
 #include "offsets.h"

arch/x86/boot/main.c

@@ -149,11 +149,6 @@ void main(void)
 	/* Query MCA information */
 	query_mca();
 
-	/* Voyager */
-#ifdef CONFIG_X86_VOYAGER
-	query_voyager();
-#endif
-
 	/* Query Intel SpeedStep (IST) information */
 	query_ist();
 

arch/x86/boot/pmjump.S

@@ -15,18 +15,15 @@
 #include <asm/boot.h>
 #include <asm/processor-flags.h>
 #include <asm/segment.h>
+#include <linux/linkage.h>
 
 	.text
-
-	.globl	protected_mode_jump
-	.type	protected_mode_jump, @function
-
 	.code16
 
 /*
  * void protected_mode_jump(u32 entrypoint, u32 bootparams);
  */
-protected_mode_jump:
+GLOBAL(protected_mode_jump)
 	movl	%edx, %esi		# Pointer to boot_params table
 
 	xorl	%ebx, %ebx
@@ -47,12 +44,10 @@ protected_mode_jump:
 	.byte	0x66, 0xea		# ljmpl opcode
 2:	.long	in_pm32			# offset
 	.word	__BOOT_CS		# segment
-
-	.size	protected_mode_jump, .-protected_mode_jump
+ENDPROC(protected_mode_jump)
 
 	.code32
-	.type	in_pm32, @function
-in_pm32:
+GLOBAL(in_pm32)
 	# Set up data segments for flat 32-bit mode
 	movl	%ecx, %ds
 	movl	%ecx, %es
@@ -78,5 +73,4 @@ in_pm32:
 	lldt	%cx
 
 	jmpl	*%eax			# Jump to the 32-bit entrypoint
-
-	.size	in_pm32, .-in_pm32
+ENDPROC(in_pm32)

arch/x86/boot/voyager.c

@@ -1,40 +0,0 @@
-/* -*- linux-c -*- ------------------------------------------------------- *
- *
- *   Copyright (C) 1991, 1992 Linus Torvalds
- *   Copyright 2007 rPath, Inc. - All Rights Reserved
- *
- *   This file is part of the Linux kernel, and is made available under
- *   the terms of the GNU General Public License version 2.
- *
- * ----------------------------------------------------------------------- */
-
-/*
- * Get the Voyager config information
- */
-
-#include "boot.h"
-
-int query_voyager(void)
-{
-	u8 err;
-	u16 es, di;
-	/* Abuse the apm_bios_info area for this */
-	u8 *data_ptr = (u8 *)&boot_params.apm_bios_info;
-
-	data_ptr[0] = 0xff;	/* Flag on config not found(?) */
-
-	asm("pushw %%es ; "
-	    "int $0x15 ; "
-	    "setc %0 ; "
-	    "movw %%es, %1 ; "
-	    "popw %%es"
-	    : "=q" (err), "=r" (es), "=D" (di)
-	    : "a" (0xffc0));
-
-	if (err)
-		return -1;	/* Not Voyager */
-
-	set_fs(es);
-	copy_from_fs(data_ptr, di, 7);	/* Table is 7 bytes apparently */
-	return 0;
-}

arch/x86/ia32/ia32_signal.c

@@ -33,8 +33,6 @@
 #include <asm/sigframe.h>
 #include <asm/sys_ia32.h>
 
-#define DEBUG_SIG 0
-
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
 #define FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_OF | \
@@ -46,78 +44,83 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
 
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
 {
-	int err;
+	int err = 0;
 
 	if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
 		return -EFAULT;
 
-	/* If you change siginfo_t structure, please make sure that
-	   this code is fixed accordingly.
-	   It should never copy any pad contained in the structure
-	   to avoid security leaks, but must copy the generic
-	   3 ints plus the relevant union member.  */
-	err = __put_user(from->si_signo, &to->si_signo);
-	err |= __put_user(from->si_errno, &to->si_errno);
-	err |= __put_user((short)from->si_code, &to->si_code);
-
-	if (from->si_code < 0) {
-		err |= __put_user(from->si_pid, &to->si_pid);
-		err |= __put_user(from->si_uid, &to->si_uid);
-		err |= __put_user(ptr_to_compat(from->si_ptr), &to->si_ptr);
-	} else {
-		/*
-		 * First 32bits of unions are always present:
-		 * si_pid === si_band === si_tid === si_addr(LS half)
-		 */
-		err |= __put_user(from->_sifields._pad[0],
-				  &to->_sifields._pad[0]);
-		switch (from->si_code >> 16) {
-		case __SI_FAULT >> 16:
-			break;
-		case __SI_CHLD >> 16:
-			err |= __put_user(from->si_utime, &to->si_utime);
-			err |= __put_user(from->si_stime, &to->si_stime);
-			err |= __put_user(from->si_status, &to->si_status);
-			/* FALL THROUGH */
-		default:
-		case __SI_KILL >> 16:
-			err |= __put_user(from->si_uid, &to->si_uid);
-			break;
-		case __SI_POLL >> 16:
-			err |= __put_user(from->si_fd, &to->si_fd);
-			break;
-		case __SI_TIMER >> 16:
-			err |= __put_user(from->si_overrun, &to->si_overrun);
-			err |= __put_user(ptr_to_compat(from->si_ptr),
-					  &to->si_ptr);
-			break;
-			 /* This is not generated by the kernel as of now.  */
-		case __SI_RT >> 16:
-		case __SI_MESGQ >> 16:
-			err |= __put_user(from->si_uid, &to->si_uid);
-			err |= __put_user(from->si_int, &to->si_int);
-			break;
+	put_user_try {
+		/* If you change siginfo_t structure, please make sure that
+		   this code is fixed accordingly.
+		   It should never copy any pad contained in the structure
+		   to avoid security leaks, but must copy the generic
+		   3 ints plus the relevant union member.  */
+		put_user_ex(from->si_signo, &to->si_signo);
+		put_user_ex(from->si_errno, &to->si_errno);
+		put_user_ex((short)from->si_code, &to->si_code);
+
+		if (from->si_code < 0) {
+			put_user_ex(from->si_pid, &to->si_pid);
+			put_user_ex(from->si_uid, &to->si_uid);
+			put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr);
+		} else {
+			/*
+			 * First 32bits of unions are always present:
+			 * si_pid === si_band === si_tid === si_addr(LS half)
+			 */
+			put_user_ex(from->_sifields._pad[0],
+					  &to->_sifields._pad[0]);
+			switch (from->si_code >> 16) {
+			case __SI_FAULT >> 16:
+				break;
+			case __SI_CHLD >> 16:
+				put_user_ex(from->si_utime, &to->si_utime);
+				put_user_ex(from->si_stime, &to->si_stime);
+				put_user_ex(from->si_status, &to->si_status);
+				/* FALL THROUGH */
+			default:
+			case __SI_KILL >> 16:
+				put_user_ex(from->si_uid, &to->si_uid);
+				break;
+			case __SI_POLL >> 16:
+				put_user_ex(from->si_fd, &to->si_fd);
+				break;
+			case __SI_TIMER >> 16:
+				put_user_ex(from->si_overrun, &to->si_overrun);
+				put_user_ex(ptr_to_compat(from->si_ptr),
+					    &to->si_ptr);
+				break;
+				 /* This is not generated by the kernel as of now.  */
+			case __SI_RT >> 16:
+			case __SI_MESGQ >> 16:
+				put_user_ex(from->si_uid, &to->si_uid);
+				put_user_ex(from->si_int, &to->si_int);
+				break;
+			}
 		}
-	}
+	} put_user_catch(err);
+
 	return err;
 }
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	int err;
+	int err = 0;
 	u32 ptr32;
 
 	if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t)))
 		return -EFAULT;
 
-	err = __get_user(to->si_signo, &from->si_signo);
-	err |= __get_user(to->si_errno, &from->si_errno);
-	err |= __get_user(to->si_code, &from->si_code);
+	get_user_try {
+		get_user_ex(to->si_signo, &from->si_signo);
+		get_user_ex(to->si_errno, &from->si_errno);
+		get_user_ex(to->si_code, &from->si_code);
 
-	err |= __get_user(to->si_pid, &from->si_pid);
-	err |= __get_user(to->si_uid, &from->si_uid);
-	err |= __get_user(ptr32, &from->si_ptr);
-	to->si_ptr = compat_ptr(ptr32);
+		get_user_ex(to->si_pid, &from->si_pid);
+		get_user_ex(to->si_uid, &from->si_uid);
+		get_user_ex(ptr32, &from->si_ptr);
+		to->si_ptr = compat_ptr(ptr32);
+	} get_user_catch(err);
 
 	return err;
 }
@@ -142,17 +145,23 @@ asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr,
 				  struct pt_regs *regs)
 {
 	stack_t uss, uoss;
-	int ret;
+	int ret, err = 0;
 	mm_segment_t seg;
 
 	if (uss_ptr) {
 		u32 ptr;
 
 		memset(&uss, 0, sizeof(stack_t));
-		if (!access_ok(VERIFY_READ, uss_ptr, sizeof(stack_ia32_t)) ||
-			    __get_user(ptr, &uss_ptr->ss_sp) ||
-			    __get_user(uss.ss_flags, &uss_ptr->ss_flags) ||
-			    __get_user(uss.ss_size, &uss_ptr->ss_size))
+		if (!access_ok(VERIFY_READ, uss_ptr, sizeof(stack_ia32_t)))
+			return -EFAULT;
+
+		get_user_try {
+			get_user_ex(ptr, &uss_ptr->ss_sp);
+			get_user_ex(uss.ss_flags, &uss_ptr->ss_flags);
+			get_user_ex(uss.ss_size, &uss_ptr->ss_size);
+		} get_user_catch(err);
+
+		if (err)
 			return -EFAULT;
 		uss.ss_sp = compat_ptr(ptr);
 	}
@@ -161,10 +170,16 @@ asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr,
 	ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, regs->sp);
 	set_fs(seg);
 	if (ret >= 0 && uoss_ptr)  {
-		if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t)) ||
-		    __put_user(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp) ||
-		    __put_user(uoss.ss_flags, &uoss_ptr->ss_flags) ||
-		    __put_user(uoss.ss_size, &uoss_ptr->ss_size))
+		if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t)))
+			return -EFAULT;
+
+		put_user_try {
+			put_user_ex(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp);
+			put_user_ex(uoss.ss_flags, &uoss_ptr->ss_flags);
+			put_user_ex(uoss.ss_size, &uoss_ptr->ss_size);
+		} put_user_catch(err);
+
+		if (err)
 			ret = -EFAULT;
 	}
 	return ret;
@@ -173,75 +188,78 @@ asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr,
 /*
  * Do a signal return; undo the signal stack.
  */
+#define loadsegment_gs(v)	load_gs_index(v)
+#define loadsegment_fs(v)	loadsegment(fs, v)
+#define loadsegment_ds(v)	loadsegment(ds, v)
+#define loadsegment_es(v)	loadsegment(es, v)
+
+#define get_user_seg(seg)	({ unsigned int v; savesegment(seg, v); v; })
+#define set_user_seg(seg, v)	loadsegment_##seg(v)
+
 #define COPY(x)			{		\
-	err |= __get_user(regs->x, &sc->x);	\
+	get_user_ex(regs->x, &sc->x);		\
 }
 
-#define COPY_SEG_CPL3(seg)	{			\
-		unsigned short tmp;			\
-		err |= __get_user(tmp, &sc->seg);	\
-		regs->seg = tmp | 3;			\
-}
+#define GET_SEG(seg)		({			\
+	unsigned short tmp;				\
+	get_user_ex(tmp, &sc->seg);			\
+	tmp;						\
+})
+
+#define COPY_SEG_CPL3(seg)	do {			\
+	regs->seg = GET_SEG(seg) | 3;			\
+} while (0)
 
 #define RELOAD_SEG(seg)		{		\
-	unsigned int cur, pre;			\
-	err |= __get_user(pre, &sc->seg);	\
-	savesegment(seg, cur);			\
+	unsigned int pre = GET_SEG(seg);	\
+	unsigned int cur = get_user_seg(seg);	\
 	pre |= 3;				\
 	if (pre != cur)				\
-		loadsegment(seg, pre);		\
+		set_user_seg(seg, pre);		\
 }
 
 static int ia32_restore_sigcontext(struct pt_regs *regs,
 				   struct sigcontext_ia32 __user *sc,
 				   unsigned int *pax)
 {
-	unsigned int tmpflags, gs, oldgs, err = 0;
+	unsigned int tmpflags, err = 0;
 	void __user *buf;
 	u32 tmp;
 
 	/* Always make any pending restarted system calls return -EINTR */
 	current_thread_info()->restart_block.fn = do_no_restart_syscall;
 
-#if DEBUG_SIG
-	printk(KERN_DEBUG "SIG restore_sigcontext: "
-	       "sc=%p err(%x) eip(%x) cs(%x) flg(%x)\n",
-	       sc, sc->err, sc->ip, sc->cs, sc->flags);
-#endif
-
-	/*
-	 * Reload fs and gs if they have changed in the signal
-	 * handler.  This does not handle long fs/gs base changes in
-	 * the handler, but does not clobber them at least in the
-	 * normal case.
-	 */
-	err |= __get_user(gs, &sc->gs);
-	gs |= 3;
-	savesegment(gs, oldgs);
-	if (gs != oldgs)
-		load_gs_index(gs);
-
-	RELOAD_SEG(fs);
-	RELOAD_SEG(ds);
-	RELOAD_SEG(es);
-
-	COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
-	COPY(dx); COPY(cx); COPY(ip);
-	/* Don't touch extended registers */
-
-	COPY_SEG_CPL3(cs);
-	COPY_SEG_CPL3(ss);
-
-	err |= __get_user(tmpflags, &sc->flags);
-	regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
-	/* disable syscall checks */
-	regs->orig_ax = -1;
-
-	err |= __get_user(tmp, &sc->fpstate);
-	buf = compat_ptr(tmp);
-	err |= restore_i387_xstate_ia32(buf);
-
-	err |= __get_user(*pax, &sc->ax);
+	get_user_try {
+		/*
+		 * Reload fs and gs if they have changed in the signal
+		 * handler.  This does not handle long fs/gs base changes in
+		 * the handler, but does not clobber them at least in the
+		 * normal case.
+		 */
+		RELOAD_SEG(gs);
+		RELOAD_SEG(fs);
+		RELOAD_SEG(ds);
+		RELOAD_SEG(es);
+
+		COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
+		COPY(dx); COPY(cx); COPY(ip);
+		/* Don't touch extended registers */
+
+		COPY_SEG_CPL3(cs);
+		COPY_SEG_CPL3(ss);
+
+		get_user_ex(tmpflags, &sc->flags);
+		regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
+		/* disable syscall checks */
+		regs->orig_ax = -1;
+
+		get_user_ex(tmp, &sc->fpstate);
+		buf = compat_ptr(tmp);
+		err |= restore_i387_xstate_ia32(buf);
+
+		get_user_ex(*pax, &sc->ax);
+	} get_user_catch(err);
+
 	return err;
 }
 
@@ -317,38 +335,36 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
 				 void __user *fpstate,
 				 struct pt_regs *regs, unsigned int mask)
 {
-	int tmp, err = 0;
-
-	savesegment(gs, tmp);
-	err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
-	savesegment(fs, tmp);
-	err |= __put_user(tmp, (unsigned int __user *)&sc->fs);
-	savesegment(ds, tmp);
-	err |= __put_user(tmp, (unsigned int __user *)&sc->ds);
-	savesegment(es, tmp);
-	err |= __put_user(tmp, (unsigned int __user *)&sc->es);
-
-	err |= __put_user(regs->di, &sc->di);
-	err |= __put_user(regs->si, &sc->si);
-	err |= __put_user(regs->bp, &sc->bp);
-	err |= __put_user(regs->sp, &sc->sp);
-	err |= __put_user(regs->bx, &sc->bx);
-	err |= __put_user(regs->dx, &sc->dx);
-	err |= __put_user(regs->cx, &sc->cx);
-	err |= __put_user(regs->ax, &sc->ax);
-	err |= __put_user(current->thread.trap_no, &sc->trapno);
-	err |= __put_user(current->thread.error_code, &sc->err);
-	err |= __put_user(regs->ip, &sc->ip);
-	err |= __put_user(regs->cs, (unsigned int __user *)&sc->cs);
-	err |= __put_user(regs->flags, &sc->flags);
-	err |= __put_user(regs->sp, &sc->sp_at_signal);
-	err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss);
-
-	err |= __put_user(ptr_to_compat(fpstate), &sc->fpstate);
-
-	/* non-iBCS2 extensions.. */
-	err |= __put_user(mask, &sc->oldmask);
-	err |= __put_user(current->thread.cr2, &sc->cr2);
+	int err = 0;
+
+	put_user_try {
+		put_user_ex(get_user_seg(gs), (unsigned int __user *)&sc->gs);
+		put_user_ex(get_user_seg(fs), (unsigned int __user *)&sc->fs);
+		put_user_ex(get_user_seg(ds), (unsigned int __user *)&sc->ds);
+		put_user_ex(get_user_seg(es), (unsigned int __user *)&sc->es);
+
+		put_user_ex(regs->di, &sc->di);
+		put_user_ex(regs->si, &sc->si);
+		put_user_ex(regs->bp, &sc->bp);
+		put_user_ex(regs->sp, &sc->sp);
+		put_user_ex(regs->bx, &sc->bx);
+		put_user_ex(regs->dx, &sc->dx);
+		put_user_ex(regs->cx, &sc->cx);
+		put_user_ex(regs->ax, &sc->ax);
+		put_user_ex(current->thread.trap_no, &sc->trapno);
+		put_user_ex(current->thread.error_code, &sc->err);
+		put_user_ex(regs->ip, &sc->ip);
+		put_user_ex(regs->cs, (unsigned int __user *)&sc->cs);
+		put_user_ex(regs->flags, &sc->flags);
+		put_user_ex(regs->sp, &sc->sp_at_signal);
+		put_user_ex(regs->ss, (unsigned int __user *)&sc->ss);
+
+		put_user_ex(ptr_to_compat(fpstate), &sc->fpstate);
+
+		/* non-iBCS2 extensions.. */
+		put_user_ex(mask, &sc->oldmask);
+		put_user_ex(current->thread.cr2, &sc->cr2);
+	} put_user_catch(err);
 
 	return err;
 }
@@ -437,13 +453,17 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 		else
 			restorer = &frame->retcode;
 	}
-	err |= __put_user(ptr_to_compat(restorer), &frame->pretcode);
 
-	/*
-	 * These are actually not used anymore, but left because some
-	 * gdb versions depend on them as a marker.
-	 */
-	err |= __put_user(*((u64 *)&code), (u64 *)frame->retcode);
+	put_user_try {
+		put_user_ex(ptr_to_compat(restorer), &frame->pretcode);
+
+		/*
+		 * These are actually not used anymore, but left because some
+		 * gdb versions depend on them as a marker.
+		 */
+		put_user_ex(*((u64 *)&code), (u64 *)frame->retcode);
+	} put_user_catch(err);
+
 	if (err)
 		return -EFAULT;
 
@@ -462,11 +482,6 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 	regs->cs = __USER32_CS;
 	regs->ss = __USER32_DS;
 
-#if DEBUG_SIG
-	printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n",
-	       current->comm, current->pid, frame, regs->ip, frame->pretcode);
-#endif
-
 	return 0;
 }
 
@@ -496,41 +511,40 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
 		return -EFAULT;
 
-	err |= __put_user(sig, &frame->sig);
-	err |= __put_user(ptr_to_compat(&frame->info), &frame->pinfo);
-	err |= __put_user(ptr_to_compat(&frame->uc), &frame->puc);
-	err |= copy_siginfo_to_user32(&frame->info, info);
-	if (err)
-		return -EFAULT;
+	put_user_try {
+		put_user_ex(sig, &frame->sig);
+		put_user_ex(ptr_to_compat(&frame->info), &frame->pinfo);
+		put_user_ex(ptr_to_compat(&frame->uc), &frame->puc);
+		err |= copy_siginfo_to_user32(&frame->info, info);
 
-	/* Create the ucontext.  */
-	if (cpu_has_xsave)
-		err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
-	else
-		err |= __put_user(0, &frame->uc.uc_flags);
-	err |= __put_user(0, &frame->uc.uc_link);
-	err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
-	err |= __put_user(sas_ss_flags(regs->sp),
-			  &frame->uc.uc_stack.ss_flags);
-	err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
-	err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
-				     regs, set->sig[0]);
-	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-	if (err)
-		return -EFAULT;
+		/* Create the ucontext.  */
+		if (cpu_has_xsave)
+			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+		else
+			put_user_ex(0, &frame->uc.uc_flags);
+		put_user_ex(0, &frame->uc.uc_link);
+		put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+		put_user_ex(sas_ss_flags(regs->sp),
+			    &frame->uc.uc_stack.ss_flags);
+		put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+		err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+					     regs, set->sig[0]);
+		err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+		if (ka->sa.sa_flags & SA_RESTORER)
+			restorer = ka->sa.sa_restorer;
+		else
+			restorer = VDSO32_SYMBOL(current->mm->context.vdso,
+						 rt_sigreturn);
+		put_user_ex(ptr_to_compat(restorer), &frame->pretcode);
+
+		/*
+		 * Not actually used anymore, but left because some gdb
+		 * versions need it.
+		 */
+		put_user_ex(*((u64 *)&code), (u64 *)frame->retcode);
+	} put_user_catch(err);
 
-	if (ka->sa.sa_flags & SA_RESTORER)
-		restorer = ka->sa.sa_restorer;
-	else
-		restorer = VDSO32_SYMBOL(current->mm->context.vdso,
-					 rt_sigreturn);
-	err |= __put_user(ptr_to_compat(restorer), &frame->pretcode);
-
-	/*
-	 * Not actually used anymore, but left because some gdb
-	 * versions need it.
-	 */
-	err |= __put_user(*((u64 *)&code), (u64 *)frame->retcode);
 	if (err)
 		return -EFAULT;
 
@@ -549,10 +563,5 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	regs->cs = __USER32_CS;
 	regs->ss = __USER32_DS;
 
-#if DEBUG_SIG
-	printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n",
-	       current->comm, current->pid, frame, regs->ip, frame->pretcode);
-#endif
-
 	return 0;
 }

arch/x86/ia32/ia32entry.S

@@ -112,8 +112,8 @@ ENTRY(ia32_sysenter_target)
 	CFI_DEF_CFA	rsp,0
 	CFI_REGISTER	rsp,rbp
 	SWAPGS_UNSAFE_STACK
-	movq	%gs:pda_kernelstack, %rsp
-	addq	$(PDA_STACKOFFSET),%rsp	
+	movq	PER_CPU_VAR(kernel_stack), %rsp
+	addq	$(KERNEL_STACK_OFFSET),%rsp
 	/*
 	 * No need to follow this irqs on/off section: the syscall
 	 * disabled irqs, here we enable it straight after entry:
@@ -273,13 +273,13 @@ ENDPROC(ia32_sysenter_target)
 ENTRY(ia32_cstar_target)
 	CFI_STARTPROC32	simple
 	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,PDA_STACKOFFSET
+	CFI_DEF_CFA	rsp,KERNEL_STACK_OFFSET
 	CFI_REGISTER	rip,rcx
 	/*CFI_REGISTER	rflags,r11*/
 	SWAPGS_UNSAFE_STACK
 	movl	%esp,%r8d
 	CFI_REGISTER	rsp,r8
-	movq	%gs:pda_kernelstack,%rsp
+	movq	PER_CPU_VAR(kernel_stack),%rsp
 	/*
 	 * No need to follow this irqs on/off section: the syscall
 	 * disabled irqs and here we enable it straight after entry:

arch/x86/include/asm/a.out-core.h

@@ -55,7 +55,7 @@ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
 	dump->regs.ds = (u16)regs->ds;
 	dump->regs.es = (u16)regs->es;
 	dump->regs.fs = (u16)regs->fs;
-	savesegment(gs, dump->regs.gs);
+	dump->regs.gs = get_user_gs(regs);
 	dump->regs.orig_ax = regs->orig_ax;
 	dump->regs.ip = regs->ip;
 	dump->regs.cs = (u16)regs->cs;

arch/x86/include/asm/acpi.h

@@ -102,9 +102,6 @@ static inline void disable_acpi(void)
 	acpi_noirq = 1;
 }
 
-/* Fixmap pages to reserve for ACPI boot-time tables (see fixmap.h) */
-#define FIX_ACPI_PAGES 4
-
 extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
 
 static inline void acpi_noirq_set(void) { acpi_noirq = 1; }

arch/x86/include/asm/apic.h

@@ -1,15 +1,18 @@
 #ifndef _ASM_X86_APIC_H
 #define _ASM_X86_APIC_H
 
-#include <linux/pm.h>
+#include <linux/cpumask.h>
 #include <linux/delay.h>
+#include <linux/pm.h>
 
 #include <asm/alternative.h>
-#include <asm/fixmap.h>
-#include <asm/apicdef.h>
+#include <asm/cpufeature.h>
 #include <asm/processor.h>
+#include <asm/apicdef.h>
+#include <asm/atomic.h>
+#include <asm/fixmap.h>
+#include <asm/mpspec.h>
 #include <asm/system.h>
-#include <asm/cpufeature.h>
 #include <asm/msr.h>
 
 #define ARCH_APICTIMER_STOPS_ON_C3	1
@@ -33,7 +36,13 @@
 	} while (0)
 
 
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
 extern void generic_apic_probe(void);
+#else
+static inline void generic_apic_probe(void)
+{
+}
+#endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
@@ -41,6 +50,21 @@ extern unsigned int apic_verbosity;
 extern int local_apic_timer_c2_ok;
 
 extern int disable_apic;
+
+#ifdef CONFIG_SMP
+extern void __inquire_remote_apic(int apicid);
+#else /* CONFIG_SMP */
+static inline void __inquire_remote_apic(int apicid)
+{
+}
+#endif /* CONFIG_SMP */
+
+static inline void default_inquire_remote_apic(int apicid)
+{
+	if (apic_verbosity >= APIC_DEBUG)
+		__inquire_remote_apic(apicid);
+}
+
 /*
  * Basic functions accessing APICs.
  */
@@ -51,7 +75,14 @@ extern int disable_apic;
 #define setup_secondary_clock setup_secondary_APIC_clock
 #endif
 
+#ifdef CONFIG_X86_VSMP
 extern int is_vsmp_box(void);
+#else
+static inline int is_vsmp_box(void)
+{
+	return 0;
+}
+#endif
 extern void xapic_wait_icr_idle(void);
 extern u32 safe_xapic_wait_icr_idle(void);
 extern void xapic_icr_write(u32, u32);
@@ -71,6 +102,12 @@ static inline u32 native_apic_mem_read(u32 reg)
 	return *((volatile u32 *)(APIC_BASE + reg));
 }
 
+extern void native_apic_wait_icr_idle(void);
+extern u32 native_safe_apic_wait_icr_idle(void);
+extern void native_apic_icr_write(u32 low, u32 id);
+extern u64 native_apic_icr_read(void);
+
+#ifdef CONFIG_X86_X2APIC
 static inline void native_apic_msr_write(u32 reg, u32 v)
 {
 	if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR ||
@@ -91,8 +128,32 @@ static inline u32 native_apic_msr_read(u32 reg)
 	return low;
 }
 
-#ifndef CONFIG_X86_32
-extern int x2apic;
+static inline void native_x2apic_wait_icr_idle(void)
+{
+	/* no need to wait for icr idle in x2apic */
+	return;
+}
+
+static inline u32 native_safe_x2apic_wait_icr_idle(void)
+{
+	/* no need to wait for icr idle in x2apic */
+	return 0;
+}
+
+static inline void native_x2apic_icr_write(u32 low, u32 id)
+{
+	wrmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low);
+}
+
+static inline u64 native_x2apic_icr_read(void)
+{
+	unsigned long val;
+
+	rdmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), val);
+	return val;
+}
+
+extern int x2apic, x2apic_phys;
 extern void check_x2apic(void);
 extern void enable_x2apic(void);
 extern void enable_IR_x2apic(void);
@@ -110,30 +171,24 @@ static inline int x2apic_enabled(void)
 	return 0;
 }
 #else
-#define x2apic_enabled()	0
+static inline void check_x2apic(void)
+{
+}
+static inline void enable_x2apic(void)
+{
+}
+static inline void enable_IR_x2apic(void)
+{
+}
+static inline int x2apic_enabled(void)
+{
+	return 0;
+}
 #endif
 
-struct apic_ops {
-	u32 (*read)(u32 reg);
-	void (*write)(u32 reg, u32 v);
-	u64 (*icr_read)(void);
-	void (*icr_write)(u32 low, u32 high);
-	void (*wait_icr_idle)(void);
-	u32 (*safe_wait_icr_idle)(void);
-};
-
-extern struct apic_ops *apic_ops;
-
-#define apic_read (apic_ops->read)
-#define apic_write (apic_ops->write)
-#define apic_icr_read (apic_ops->icr_read)
-#define apic_icr_write (apic_ops->icr_write)
-#define apic_wait_icr_idle (apic_ops->wait_icr_idle)
-#define safe_apic_wait_icr_idle (apic_ops->safe_wait_icr_idle)
-
 extern int get_physical_broadcast(void);
 
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_X2APIC
 static inline void ack_x2APIC_irq(void)
 {
 	/* Docs say use 0 for future compatibility */
@@ -141,18 +196,6 @@ static inline void ack_x2APIC_irq(void)
 }
 #endif
 
-
-static inline void ack_APIC_irq(void)
-{
-	/*
-	 * ack_APIC_irq() actually gets compiled as a single instruction
-	 * ... yummie.
-	 */
-
-	/* Docs say use 0 for future compatibility */
-	apic_write(APIC_EOI, 0);
-}
-
 extern int lapic_get_maxlvt(void);
 extern void clear_local_APIC(void);
 extern void connect_bsp_APIC(void);
@@ -196,4 +239,327 @@ static inline void disable_local_APIC(void) { }
 
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
+#ifdef CONFIG_X86_64
+#define	SET_APIC_ID(x)		(apic->set_apic_id(x))
+#else
+
+#endif
+
+/*
+ * Copyright 2004 James Cleverdon, IBM.
+ * Subject to the GNU Public License, v.2
+ *
+ * Generic APIC sub-arch data struct.
+ *
+ * Hacked for x86-64 by James Cleverdon from i386 architecture code by
+ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
+ * James Cleverdon.
+ */
+struct apic {
+	char *name;
+
+	int (*probe)(void);
+	int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
+	int (*apic_id_registered)(void);
+
+	u32 irq_delivery_mode;
+	u32 irq_dest_mode;
+
+	const struct cpumask *(*target_cpus)(void);
+
+	int disable_esr;
+
+	int dest_logical;
+	unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid);
+	unsigned long (*check_apicid_present)(int apicid);
+
+	void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
+	void (*init_apic_ldr)(void);
+
+	physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map);
+
+	void (*setup_apic_routing)(void);
+	int (*multi_timer_check)(int apic, int irq);
+	int (*apicid_to_node)(int logical_apicid);
+	int (*cpu_to_logical_apicid)(int cpu);
+	int (*cpu_present_to_apicid)(int mps_cpu);
+	physid_mask_t (*apicid_to_cpu_present)(int phys_apicid);
+	void (*setup_portio_remap)(void);
+	int (*check_phys_apicid_present)(int boot_cpu_physical_apicid);
+	void (*enable_apic_mode)(void);
+	int (*phys_pkg_id)(int cpuid_apic, int index_msb);
+
+	/*
+	 * When one of the next two hooks returns 1 the apic
+	 * is switched to this. Essentially they are additional
+	 * probe functions:
+	 */
+	int (*mps_oem_check)(struct mpc_table *mpc, char *oem, char *productid);
+
+	unsigned int (*get_apic_id)(unsigned long x);
+	unsigned long (*set_apic_id)(unsigned int id);
+	unsigned long apic_id_mask;
+
+	unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
+	unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
+					       const struct cpumask *andmask);
+
+	/* ipi */
+	void (*send_IPI_mask)(const struct cpumask *mask, int vector);
+	void (*send_IPI_mask_allbutself)(const struct cpumask *mask,
+					 int vector);
+	void (*send_IPI_allbutself)(int vector);
+	void (*send_IPI_all)(int vector);
+	void (*send_IPI_self)(int vector);
+
+	/* wakeup_secondary_cpu */
+	int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
+
+	int trampoline_phys_low;
+	int trampoline_phys_high;
+
+	void (*wait_for_init_deassert)(atomic_t *deassert);
+	void (*smp_callin_clear_local_apic)(void);
+	void (*inquire_remote_apic)(int apicid);
+
+	/* apic ops */
+	u32 (*read)(u32 reg);
+	void (*write)(u32 reg, u32 v);
+	u64 (*icr_read)(void);
+	void (*icr_write)(u32 low, u32 high);
+	void (*wait_icr_idle)(void);
+	u32 (*safe_wait_icr_idle)(void);
+};
+
+/*
+ * Pointer to the local APIC driver in use on this system (there's
+ * always just one such driver in use - the kernel decides via an
+ * early probing process which one it picks - and then sticks to it):
+ */
+extern struct apic *apic;
+
+/*
+ * APIC functionality to boot other CPUs - only used on SMP:
+ */
+#ifdef CONFIG_SMP
+extern atomic_t init_deasserted;
+extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
+#endif
+
+static inline u32 apic_read(u32 reg)
+{
+	return apic->read(reg);
+}
+
+static inline void apic_write(u32 reg, u32 val)
+{
+	apic->write(reg, val);
+}
+
+static inline u64 apic_icr_read(void)
+{
+	return apic->icr_read();
+}
+
+static inline void apic_icr_write(u32 low, u32 high)
+{
+	apic->icr_write(low, high);
+}
+
+static inline void apic_wait_icr_idle(void)
+{
+	apic->wait_icr_idle();
+}
+
+static inline u32 safe_apic_wait_icr_idle(void)
+{
+	return apic->safe_wait_icr_idle();
+}
+
+
+static inline void ack_APIC_irq(void)
+{
+	/*
+	 * ack_APIC_irq() actually gets compiled as a single instruction
+	 * ... yummie.
+	 */
+
+	/* Docs say use 0 for future compatibility */
+	apic_write(APIC_EOI, 0);
+}
+
+static inline unsigned default_get_apic_id(unsigned long x)
+{
+	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
+
+	if (APIC_XAPIC(ver))
+		return (x >> 24) & 0xFF;
+	else
+		return (x >> 24) & 0x0F;
+}
+
+/*
+ * Warm reset vector default position:
+ */
+#define DEFAULT_TRAMPOLINE_PHYS_LOW		0x467
+#define DEFAULT_TRAMPOLINE_PHYS_HIGH		0x469
+
+#ifdef CONFIG_X86_64
+extern struct apic apic_flat;
+extern struct apic apic_physflat;
+extern struct apic apic_x2apic_cluster;
+extern struct apic apic_x2apic_phys;
+extern int default_acpi_madt_oem_check(char *, char *);
+
+extern void apic_send_IPI_self(int vector);
+
+extern struct apic apic_x2apic_uv_x;
+DECLARE_PER_CPU(int, x2apic_extra_bits);
+
+extern int default_cpu_present_to_apicid(int mps_cpu);
+extern int default_check_phys_apicid_present(int boot_cpu_physical_apicid);
+#endif
+
+static inline void default_wait_for_init_deassert(atomic_t *deassert)
+{
+	while (!atomic_read(deassert))
+		cpu_relax();
+	return;
+}
+
+extern void generic_bigsmp_probe(void);
+
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+#include <asm/smp.h>
+
+#define APIC_DFR_VALUE	(APIC_DFR_FLAT)
+
+static inline const struct cpumask *default_target_cpus(void)
+{
+#ifdef CONFIG_SMP
+	return cpu_online_mask;
+#else
+	return cpumask_of(0);
+#endif
+}
+
+DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
+
+
+static inline unsigned int read_apic_id(void)
+{
+	unsigned int reg;
+
+	reg = apic_read(APIC_ID);
+
+	return apic->get_apic_id(reg);
+}
+
+extern void default_setup_apic_routing(void);
+
+#ifdef CONFIG_X86_32
+/*
+ * Set up the logical destination ID.
+ *
+ * Intel recommends to set DFR, LDR and TPR before enabling
+ * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
+ * document number 292116).  So here it goes...
+ */
+extern void default_init_apic_ldr(void);
+
+static inline int default_apic_id_registered(void)
+{
+	return physid_isset(read_apic_id(), phys_cpu_present_map);
+}
+
+static inline unsigned int
+default_cpu_mask_to_apicid(const struct cpumask *cpumask)
+{
+	return cpumask_bits(cpumask)[0];
+}
+
+static inline unsigned int
+default_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+			       const struct cpumask *andmask)
+{
+	unsigned long mask1 = cpumask_bits(cpumask)[0];
+	unsigned long mask2 = cpumask_bits(andmask)[0];
+	unsigned long mask3 = cpumask_bits(cpu_online_mask)[0];
+
+	return (unsigned int)(mask1 & mask2 & mask3);
+}
+
+static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
+{
+	return cpuid_apic >> index_msb;
+}
+
+extern int default_apicid_to_node(int logical_apicid);
+
+#endif
+
+static inline unsigned long default_check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+	return physid_isset(apicid, bitmap);
+}
+
+static inline unsigned long default_check_apicid_present(int bit)
+{
+	return physid_isset(bit, phys_cpu_present_map);
+}
+
+static inline physid_mask_t default_ioapic_phys_id_map(physid_mask_t phys_map)
+{
+	return phys_map;
+}
+
+/* Mapping from cpu number to logical apicid */
+static inline int default_cpu_to_logical_apicid(int cpu)
+{
+	return 1 << cpu;
+}
+
+static inline int __default_cpu_present_to_apicid(int mps_cpu)
+{
+	if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu))
+		return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
+	else
+		return BAD_APICID;
+}
+
+static inline int
+__default_check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+	return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map);
+}
+
+#ifdef CONFIG_X86_32
+static inline int default_cpu_present_to_apicid(int mps_cpu)
+{
+	return __default_cpu_present_to_apicid(mps_cpu);
+}
+
+static inline int
+default_check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+	return __default_check_phys_apicid_present(boot_cpu_physical_apicid);
+}
+#else
+extern int default_cpu_present_to_apicid(int mps_cpu);
+extern int default_check_phys_apicid_present(int boot_cpu_physical_apicid);
+#endif
+
+static inline physid_mask_t default_apicid_to_cpu_present(int phys_apicid)
+{
+	return physid_mask_of_physid(phys_apicid);
+}
+
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#ifdef CONFIG_X86_32
+extern u8 cpu_2_logical_apicid[NR_CPUS];
+#endif
+
 #endif /* _ASM_X86_APIC_H */

arch/x86/include/asm/apicnum.h

@@ -0,0 +1,12 @@
+#ifndef _ASM_X86_APICNUM_H
+#define _ASM_X86_APICNUM_H
+
+/* define MAX_IO_APICS */
+#ifdef CONFIG_X86_32
+# define MAX_IO_APICS 64
+#else
+# define MAX_IO_APICS 128
+# define MAX_LOCAL_APIC 32768
+#endif
+
+#endif /* _ASM_X86_APICNUM_H */

arch/x86/include/asm/arch_hooks.h

@@ -1,26 +0,0 @@
-#ifndef _ASM_X86_ARCH_HOOKS_H
-#define _ASM_X86_ARCH_HOOKS_H
-
-#include <linux/interrupt.h>
-
-/*
- *	linux/include/asm/arch_hooks.h
- *
- *	define the architecture specific hooks
- */
-
-/* these aren't arch hooks, they are generic routines
- * that can be used by the hooks */
-extern void init_ISA_irqs(void);
-extern irqreturn_t timer_interrupt(int irq, void *dev_id);
-
-/* these are the defined hooks */
-extern void intr_init_hook(void);
-extern void pre_intr_init_hook(void);
-extern void pre_setup_arch_hook(void);
-extern void trap_init_hook(void);
-extern void pre_time_init_hook(void);
-extern void time_init_hook(void);
-extern void mca_nmi_hook(void);
-
-#endif /* _ASM_X86_ARCH_HOOKS_H */

arch/x86/include/asm/bigsmp/apic.h

@@ -1,155 +0,0 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
-
-#define xapic_phys_to_log_apicid(cpu) (per_cpu(x86_bios_cpu_apicid, cpu))
-#define esr_disable (1)
-
-static inline int apic_id_registered(void)
-{
-	return (1);
-}
-
-static inline const cpumask_t *target_cpus(void)
-{
-#ifdef CONFIG_SMP
-	return &cpu_online_map;
-#else
-	return &cpumask_of_cpu(0);
-#endif
-}
-
-#undef APIC_DEST_LOGICAL
-#define APIC_DEST_LOGICAL	0
-#define APIC_DFR_VALUE		(APIC_DFR_FLAT)
-#define INT_DELIVERY_MODE	(dest_Fixed)
-#define INT_DEST_MODE		(0)    /* phys delivery to target proc */
-#define NO_BALANCE_IRQ		(0)
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-	return (0);
-}
-
-static inline unsigned long check_apicid_present(int bit)
-{
-	return (1);
-}
-
-static inline unsigned long calculate_ldr(int cpu)
-{
-	unsigned long val, id;
-	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-	id = xapic_phys_to_log_apicid(cpu);
-	val |= SET_APIC_LOGICAL_ID(id);
-	return val;
-}
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr(void)
-{
-	unsigned long val;
-	int cpu = smp_processor_id();
-
-	apic_write(APIC_DFR, APIC_DFR_VALUE);
-	val = calculate_ldr(cpu);
-	apic_write(APIC_LDR, val);
-}
-
-static inline void setup_apic_routing(void)
-{
-	printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
-		"Physflat", nr_ioapics);
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-	return (0);
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-	return apicid_2_node[hard_smp_processor_id()];
-}
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (mps_cpu < nr_cpu_ids)
-		return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
-
-	return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
-{
-	return physid_mask_of_physid(phys_apicid);
-}
-
-extern u8 cpu_2_logical_apicid[];
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return cpu_physical_id(cpu);
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-	/* For clustered we don't have a good way to do this yet - hack */
-	return physids_promote(0xFFL);
-}
-
-static inline void setup_portio_remap(void)
-{
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-	return (1);
-}
-
-/* As we are using single CPU as destination, pick only one CPU here */
-static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
-{
-	int cpu;
-	int apicid;	
-
-	cpu = first_cpu(*cpumask);
-	apicid = cpu_to_logical_apicid(cpu);
-	return apicid;
-}
-
-static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *cpumask,
-						  const struct cpumask *andmask)
-{
-	int cpu;
-
-	/*
-	 * We're using fixed IRQ delivery, can only return one phys APIC ID.
-	 * May as well be the first.
-	 */
-	for_each_cpu_and(cpu, cpumask, andmask)
-		if (cpumask_test_cpu(cpu, cpu_online_mask))
-			break;
-	if (cpu < nr_cpu_ids)
-		return cpu_to_logical_apicid(cpu);
-
-	return BAD_APICID;
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_MACH_APIC_H */

arch/x86/include/asm/bigsmp/apicdef.h

@@ -1,13 +0,0 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
-
-#define		APIC_ID_MASK		(0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-	return (((x)>>24)&0xFF);
-}
-
-#define		GET_APIC_ID(x)	get_apic_id(x)
-
-#endif

arch/x86/include/asm/bigsmp/ipi.h

@@ -1,22 +0,0 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
-
-void send_IPI_mask_sequence(const struct cpumask *mask, int vector);
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector);
-
-static inline void send_IPI_mask(const struct cpumask *mask, int vector)
-{
-	send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-	send_IPI_mask_allbutself(cpu_online_mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-	send_IPI_mask(cpu_online_mask, vector);
-}
-
-#endif /* __ASM_MACH_IPI_H */

arch/x86/include/asm/boot.h

@@ -10,17 +10,31 @@
 #define EXTENDED_VGA	0xfffe		/* 80x50 mode */
 #define ASK_VGA		0xfffd		/* ask for it at bootup */
 
+#ifdef __KERNEL__
+
 /* Physical address where kernel should be loaded. */
 #define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
 				+ (CONFIG_PHYSICAL_ALIGN - 1)) \
 				& ~(CONFIG_PHYSICAL_ALIGN - 1))
 
+#ifdef CONFIG_KERNEL_BZIP2
+#define BOOT_HEAP_SIZE             0x400000
+#else /* !CONFIG_KERNEL_BZIP2 */
+
 #ifdef CONFIG_X86_64
 #define BOOT_HEAP_SIZE	0x7000
-#define BOOT_STACK_SIZE	0x4000
 #else
 #define BOOT_HEAP_SIZE	0x4000
+#endif
+
+#endif /* !CONFIG_KERNEL_BZIP2 */
+
+#ifdef CONFIG_X86_64
+#define BOOT_STACK_SIZE	0x4000
+#else
 #define BOOT_STACK_SIZE	0x1000
 #endif
 
+#endif /* __KERNEL__ */
+
 #endif /* _ASM_X86_BOOT_H */

arch/x86/include/asm/cacheflush.h

@@ -5,24 +5,43 @@
 #include <linux/mm.h>
 
 /* Caches aren't brain-dead on the intel. */
-#define flush_cache_all()			do { } while (0)
-#define flush_cache_mm(mm)			do { } while (0)
-#define flush_cache_dup_mm(mm)			do { } while (0)
-#define flush_cache_range(vma, start, end)	do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
-#define flush_dcache_page(page)			do { } while (0)
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
-#define flush_icache_range(start, end)		do { } while (0)
-#define flush_icache_page(vma, pg)		do { } while (0)
-#define flush_icache_user_range(vma, pg, adr, len)	do { } while (0)
-#define flush_cache_vmap(start, end)		do { } while (0)
-#define flush_cache_vunmap(start, end)		do { } while (0)
+static inline void flush_cache_all(void) { }
+static inline void flush_cache_mm(struct mm_struct *mm) { }
+static inline void flush_cache_dup_mm(struct mm_struct *mm) { }
+static inline void flush_cache_range(struct vm_area_struct *vma,
+				     unsigned long start, unsigned long end) { }
+static inline void flush_cache_page(struct vm_area_struct *vma,
+				    unsigned long vmaddr, unsigned long pfn) { }
+static inline void flush_dcache_page(struct page *page) { }
+static inline void flush_dcache_mmap_lock(struct address_space *mapping) { }
+static inline void flush_dcache_mmap_unlock(struct address_space *mapping) { }
+static inline void flush_icache_range(unsigned long start,
+				      unsigned long end) { }
+static inline void flush_icache_page(struct vm_area_struct *vma,
+				     struct page *page) { }
+static inline void flush_icache_user_range(struct vm_area_struct *vma,
+					   struct page *page,
+					   unsigned long addr,
+					   unsigned long len) { }
+static inline void flush_cache_vmap(unsigned long start, unsigned long end) { }
+static inline void flush_cache_vunmap(unsigned long start,
+				      unsigned long end) { }
 
-#define copy_to_user_page(vma, page, vaddr, dst, src, len)	\
-	memcpy((dst), (src), (len))
-#define copy_from_user_page(vma, page, vaddr, dst, src, len)	\
-	memcpy((dst), (src), (len))
+static inline void copy_to_user_page(struct vm_area_struct *vma,
+				     struct page *page, unsigned long vaddr,
+				     void *dst, const void *src,
+				     unsigned long len)
+{
+	memcpy(dst, src, len);
+}
+
+static inline void copy_from_user_page(struct vm_area_struct *vma,
+				       struct page *page, unsigned long vaddr,
+				       void *dst, const void *src,
+				       unsigned long len)
+{
+	memcpy(dst, src, len);
+}
 
 #define PG_non_WB				PG_arch_1
 PAGEFLAG(NonWB, non_WB)

arch/x86/include/asm/calling.h

@@ -1,5 +1,55 @@
 /*
- * Some macros to handle stack frames in assembly.
+
+ x86 function call convention, 64-bit:
+ -------------------------------------
+  arguments           |  callee-saved      | extra caller-saved | return
+ [callee-clobbered]   |                    | [callee-clobbered] |
+ ---------------------------------------------------------------------------
+ rdi rsi rdx rcx r8-9 | rbx rbp [*] r12-15 | r10-11             | rax, rdx [**]
+
+ ( rsp is obviously invariant across normal function calls. (gcc can 'merge'
+   functions when it sees tail-call optimization possibilities) rflags is
+   clobbered. Leftover arguments are passed over the stack frame.)
+
+ [*]  In the frame-pointers case rbp is fixed to the stack frame.
+
+ [**] for struct return values wider than 64 bits the return convention is a
+      bit more complex: up to 128 bits width we return small structures
+      straight in rax, rdx. For structures larger than that (3 words or
+      larger) the caller puts a pointer to an on-stack return struct
+      [allocated in the caller's stack frame] into the first argument - i.e.
+      into rdi. All other arguments shift up by one in this case.
+      Fortunately this case is rare in the kernel.
+
+For 32-bit we have the following conventions - kernel is built with
+-mregparm=3 and -freg-struct-return:
+
+ x86 function calling convention, 32-bit:
+ ----------------------------------------
+  arguments         | callee-saved        | extra caller-saved | return
+ [callee-clobbered] |                     | [callee-clobbered] |
+ -------------------------------------------------------------------------
+ eax edx ecx        | ebx edi esi ebp [*] | <none>             | eax, edx [**]
+
+ ( here too esp is obviously invariant across normal function calls. eflags
+   is clobbered. Leftover arguments are passed over the stack frame. )
+
+ [*]  In the frame-pointers case ebp is fixed to the stack frame.
+
+ [**] We build with -freg-struct-return, which on 32-bit means similar
+      semantics as on 64-bit: edx can be used for a second return value
+      (i.e. covering integer and structure sizes up to 64 bits) - after that
+      it gets more complex and more expensive: 3-word or larger struct returns
+      get done in the caller's frame and the pointer to the return struct goes
+      into regparm0, i.e. eax - the other arguments shift up and the
+      function's register parameters degenerate to regparm=2 in essence.
+
+*/
+
+
+/*
+ * 64-bit system call stack frame layout defines and helpers,
+ * for assembly code:
  */
 
 #define R15		  0
@@ -9,7 +59,7 @@
 #define RBP		 32
 #define RBX		 40
 
-/* arguments: interrupts/non tracing syscalls only save upto here*/
+/* arguments: interrupts/non tracing syscalls only save up to here: */
 #define R11		 48
 #define R10		 56
 #define R9		 64
@@ -22,7 +72,7 @@
 #define ORIG_RAX	120       /* + error_code */
 /* end of arguments */
 
-/* cpu exception frame or undefined in case of fast syscall. */
+/* cpu exception frame or undefined in case of fast syscall: */
 #define RIP		128
 #define CS		136
 #define EFLAGS		144

arch/x86/include/asm/cpu.h

@@ -7,6 +7,20 @@
 #include <linux/nodemask.h>
 #include <linux/percpu.h>
 
+#ifdef CONFIG_SMP
+
+extern void prefill_possible_map(void);
+
+#else /* CONFIG_SMP */
+
+static inline void prefill_possible_map(void) {}
+
+#define cpu_physical_id(cpu)			boot_cpu_physical_apicid
+#define safe_smp_processor_id()			0
+#define stack_smp_processor_id()		0
+
+#endif /* CONFIG_SMP */
+
 struct x86_cpu {
 	struct cpu cpu;
 };
@@ -17,4 +31,7 @@ extern void arch_unregister_cpu(int);
 #endif
 
 DECLARE_PER_CPU(int, cpu_state);
+
+extern unsigned int boot_cpu_id;
+
 #endif /* _ASM_X86_CPU_H */

arch/x86/include/asm/cpumask.h

@@ -0,0 +1,32 @@
+#ifndef _ASM_X86_CPUMASK_H
+#define _ASM_X86_CPUMASK_H
+#ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
+
+#ifdef CONFIG_X86_64
+
+extern cpumask_var_t cpu_callin_mask;
+extern cpumask_var_t cpu_callout_mask;
+extern cpumask_var_t cpu_initialized_mask;
+extern cpumask_var_t cpu_sibling_setup_mask;
+
+extern void setup_cpu_local_masks(void);
+
+#else /* CONFIG_X86_32 */
+
+extern cpumask_t cpu_callin_map;
+extern cpumask_t cpu_callout_map;
+extern cpumask_t cpu_initialized;
+extern cpumask_t cpu_sibling_setup_map;
+
+#define cpu_callin_mask		((struct cpumask *)&cpu_callin_map)
+#define cpu_callout_mask	((struct cpumask *)&cpu_callout_map)
+#define cpu_initialized_mask	((struct cpumask *)&cpu_initialized)
+#define cpu_sibling_setup_mask	((struct cpumask *)&cpu_sibling_setup_map)
+
+static inline void setup_cpu_local_masks(void) { }
+
+#endif /* CONFIG_X86_32 */
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_CPUMASK_H */

arch/x86/include/asm/current.h

@@ -1,39 +1,21 @@
 #ifndef _ASM_X86_CURRENT_H
 #define _ASM_X86_CURRENT_H
 
-#ifdef CONFIG_X86_32
 #include <linux/compiler.h>
 #include <asm/percpu.h>
 
+#ifndef __ASSEMBLY__
 struct task_struct;
 
 DECLARE_PER_CPU(struct task_struct *, current_task);
-static __always_inline struct task_struct *get_current(void)
-{
-	return x86_read_percpu(current_task);
-}
-
-#else /* X86_32 */
-
-#ifndef __ASSEMBLY__
-#include <asm/pda.h>
-
-struct task_struct;
 
 static __always_inline struct task_struct *get_current(void)
 {
-	return read_pda(pcurrent);
+	return percpu_read(current_task);
 }
 
-#else /* __ASSEMBLY__ */
-
-#include <asm/asm-offsets.h>
-#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
+#define current get_current()
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* X86_32 */
-
-#define current get_current()
-
 #endif /* _ASM_X86_CURRENT_H */

arch/x86/include/asm/elf.h

@@ -112,7 +112,7 @@ extern unsigned int vdso_enabled;
  * now struct_user_regs, they are different)
  */
 
-#define ELF_CORE_COPY_REGS(pr_reg, regs)	\
+#define ELF_CORE_COPY_REGS_COMMON(pr_reg, regs)	\
 do {						\
 	pr_reg[0] = regs->bx;			\
 	pr_reg[1] = regs->cx;			\
@@ -124,7 +124,6 @@ do {						\
 	pr_reg[7] = regs->ds & 0xffff;		\
 	pr_reg[8] = regs->es & 0xffff;		\
 	pr_reg[9] = regs->fs & 0xffff;		\
-	savesegment(gs, pr_reg[10]);		\
 	pr_reg[11] = regs->orig_ax;		\
 	pr_reg[12] = regs->ip;			\
 	pr_reg[13] = regs->cs & 0xffff;		\
@@ -133,6 +132,18 @@ do {						\
 	pr_reg[16] = regs->ss & 0xffff;		\
 } while (0);
 
+#define ELF_CORE_COPY_REGS(pr_reg, regs)	\
+do {						\
+	ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\
+	pr_reg[10] = get_user_gs(regs);		\
+} while (0);
+
+#define ELF_CORE_COPY_KERNEL_REGS(pr_reg, regs)	\
+do {						\
+	ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\
+	savesegment(gs, pr_reg[10]);		\
+} while (0);
+
 #define ELF_PLATFORM	(utsname()->machine)
 #define set_personality_64bit()	do { } while (0)
 

arch/x86/include/asm/mach-default/entry_arch.h → arch/x86/include/asm/entry_arch.h

@@ -9,12 +9,28 @@
  * is no hardware IRQ pin equivalent for them, they are triggered
  * through the ICC by us (IPIs)
  */
-#ifdef CONFIG_X86_SMP
+#ifdef CONFIG_SMP
 BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
-BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR)
 BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
 BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
+
+BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt1,INVALIDATE_TLB_VECTOR_START+1,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt2,INVALIDATE_TLB_VECTOR_START+2,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt3,INVALIDATE_TLB_VECTOR_START+3,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt4,INVALIDATE_TLB_VECTOR_START+4,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt5,INVALIDATE_TLB_VECTOR_START+5,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt6,INVALIDATE_TLB_VECTOR_START+6,
+		 smp_invalidate_interrupt)
+BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7,
+		 smp_invalidate_interrupt)
 #endif
 
 /*
@@ -25,10 +41,15 @@ BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
  * a much simpler SMP time architecture:
  */
 #ifdef CONFIG_X86_LOCAL_APIC
+
 BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR)
 BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
 BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
 
+#ifdef CONFIG_PERF_COUNTERS
+BUILD_INTERRUPT(perf_counter_interrupt, LOCAL_PERF_VECTOR)
+#endif
+
 #ifdef CONFIG_X86_MCE_P4THERMAL
 BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
 #endif

arch/x86/include/asm/es7000/apic.h

@@ -1,242 +0,0 @@
-#ifndef __ASM_ES7000_APIC_H
-#define __ASM_ES7000_APIC_H
-
-#include <linux/gfp.h>
-
-#define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu)
-#define esr_disable (1)
-
-static inline int apic_id_registered(void)
-{
-	        return (1);
-}
-
-static inline const cpumask_t *target_cpus_cluster(void)
-{
-	return &CPU_MASK_ALL;
-}
-
-static inline const cpumask_t *target_cpus(void)
-{
-	return &cpumask_of_cpu(smp_processor_id());
-}
-
-#define APIC_DFR_VALUE_CLUSTER		(APIC_DFR_CLUSTER)
-#define INT_DELIVERY_MODE_CLUSTER	(dest_LowestPrio)
-#define INT_DEST_MODE_CLUSTER		(1) /* logical delivery broadcast to all procs */
-#define NO_BALANCE_IRQ_CLUSTER		(1)
-
-#define APIC_DFR_VALUE		(APIC_DFR_FLAT)
-#define INT_DELIVERY_MODE	(dest_Fixed)
-#define INT_DEST_MODE		(0)    /* phys delivery to target procs */
-#define NO_BALANCE_IRQ		(0)
-#undef  APIC_DEST_LOGICAL
-#define APIC_DEST_LOGICAL	0x0
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-	return 0;
-}
-static inline unsigned long check_apicid_present(int bit)
-{
-	return physid_isset(bit, phys_cpu_present_map);
-}
-
-#define apicid_cluster(apicid) (apicid & 0xF0)
-
-static inline unsigned long calculate_ldr(int cpu)
-{
-	unsigned long id;
-	id = xapic_phys_to_log_apicid(cpu);
-	return (SET_APIC_LOGICAL_ID(id));
-}
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LdR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr_cluster(void)
-{
-	unsigned long val;
-	int cpu = smp_processor_id();
-
-	apic_write(APIC_DFR, APIC_DFR_VALUE_CLUSTER);
-	val = calculate_ldr(cpu);
-	apic_write(APIC_LDR, val);
-}
-
-static inline void init_apic_ldr(void)
-{
-	unsigned long val;
-	int cpu = smp_processor_id();
-
-	apic_write(APIC_DFR, APIC_DFR_VALUE);
-	val = calculate_ldr(cpu);
-	apic_write(APIC_LDR, val);
-}
-
-extern int apic_version [MAX_APICS];
-static inline void setup_apic_routing(void)
-{
-	int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id());
-	printk("Enabling APIC mode:  %s. Using %d I/O APICs, target cpus %lx\n",
-		(apic_version[apic] == 0x14) ?
-			"Physical Cluster" : "Logical Cluster",
-			nr_ioapics, cpus_addr(*target_cpus())[0]);
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-	return 0;
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-	return 0;
-}
-
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (!mps_cpu)
-		return boot_cpu_physical_apicid;
-	else if (mps_cpu < nr_cpu_ids)
-		return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
-	else
-		return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
-{
-	static int id = 0;
-	physid_mask_t mask;
-	mask = physid_mask_of_physid(id);
-	++id;
-	return mask;
-}
-
-extern u8 cpu_2_logical_apicid[];
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
-	if (cpu >= nr_cpu_ids)
-		return BAD_APICID;
-	return (int)cpu_2_logical_apicid[cpu];
-#else
-	return logical_smp_processor_id();
-#endif
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-	/* For clustered we don't have a good way to do this yet - hack */
-	return physids_promote(0xff);
-}
-
-
-static inline void setup_portio_remap(void)
-{
-}
-
-extern unsigned int boot_cpu_physical_apicid;
-static inline int check_phys_apicid_present(int cpu_physical_apicid)
-{
-	boot_cpu_physical_apicid = read_apic_id();
-	return (1);
-}
-
-static inline unsigned int
-cpu_mask_to_apicid_cluster(const struct cpumask *cpumask)
-{
-	int num_bits_set;
-	int cpus_found = 0;
-	int cpu;
-	int apicid;
-
-	num_bits_set = cpumask_weight(cpumask);
-	/* Return id to all */
-	if (num_bits_set == nr_cpu_ids)
-		return 0xFF;
-	/*
-	 * The cpus in the mask must all be on the apic cluster.  If are not
-	 * on the same apicid cluster return default value of TARGET_CPUS.
-	 */
-	cpu = cpumask_first(cpumask);
-	apicid = cpu_to_logical_apicid(cpu);
-	while (cpus_found < num_bits_set) {
-		if (cpumask_test_cpu(cpu, cpumask)) {
-			int new_apicid = cpu_to_logical_apicid(cpu);
-			if (apicid_cluster(apicid) !=
-					apicid_cluster(new_apicid)){
-				printk ("%s: Not a valid mask!\n", __func__);
-				return 0xFF;
-			}
-			apicid = new_apicid;
-			cpus_found++;
-		}
-		cpu++;
-	}
-	return apicid;
-}
-
-static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask)
-{
-	int num_bits_set;
-	int cpus_found = 0;
-	int cpu;
-	int apicid;
-
-	num_bits_set = cpus_weight(*cpumask);
-	/* Return id to all */
-	if (num_bits_set == nr_cpu_ids)
-		return cpu_to_logical_apicid(0);
-	/*
-	 * The cpus in the mask must all be on the apic cluster.  If are not
-	 * on the same apicid cluster return default value of TARGET_CPUS.
-	 */
-	cpu = first_cpu(*cpumask);
-	apicid = cpu_to_logical_apicid(cpu);
-	while (cpus_found < num_bits_set) {
-		if (cpu_isset(cpu, *cpumask)) {
-			int new_apicid = cpu_to_logical_apicid(cpu);
-			if (apicid_cluster(apicid) !=
-					apicid_cluster(new_apicid)){
-				printk ("%s: Not a valid mask!\n", __func__);
-				return cpu_to_logical_apicid(0);
-			}
-			apicid = new_apicid;
-			cpus_found++;
-		}
-		cpu++;
-	}
-	return apicid;
-}
-
-
-static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *inmask,
-						  const struct cpumask *andmask)
-{
-	int apicid = cpu_to_logical_apicid(0);
-	cpumask_var_t cpumask;
-
-	if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
-		return apicid;
-
-	cpumask_and(cpumask, inmask, andmask);
-	cpumask_and(cpumask, cpumask, cpu_online_mask);
-	apicid = cpu_mask_to_apicid(cpumask);
-
-	free_cpumask_var(cpumask);
-	return apicid;
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_ES7000_APIC_H */

arch/x86/include/asm/es7000/apicdef.h

@@ -1,13 +0,0 @@
-#ifndef __ASM_ES7000_APICDEF_H
-#define __ASM_ES7000_APICDEF_H
-
-#define		APIC_ID_MASK		(0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-	return (((x)>>24)&0xFF);
-}
-
-#define		GET_APIC_ID(x)	get_apic_id(x)
-
-#endif

arch/x86/include/asm/es7000/ipi.h

@@ -1,22 +0,0 @@
-#ifndef __ASM_ES7000_IPI_H
-#define __ASM_ES7000_IPI_H
-
-void send_IPI_mask_sequence(const struct cpumask *mask, int vector);
-void send_IPI_mask_allbutself(const struct cpumask *mask, int vector);
-
-static inline void send_IPI_mask(const struct cpumask *mask, int vector)
-{
-	send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-	send_IPI_mask_allbutself(cpu_online_mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-	send_IPI_mask(cpu_online_mask, vector);
-}
-
-#endif /* __ASM_ES7000_IPI_H */

arch/x86/include/asm/es7000/mpparse.h

@@ -1,29 +0,0 @@
-#ifndef __ASM_ES7000_MPPARSE_H
-#define __ASM_ES7000_MPPARSE_H
-
-#include <linux/acpi.h>
-
-extern int parse_unisys_oem (char *oemptr);
-extern int find_unisys_acpi_oem_table(unsigned long *oem_addr);
-extern void unmap_unisys_acpi_oem_table(unsigned long oem_addr);
-extern void setup_unisys(void);
-
-#ifndef CONFIG_X86_GENERICARCH
-extern int acpi_madt_oem_check(char *oem_id, char *oem_table_id);
-extern int mps_oem_check(struct mpc_table *mpc, char *oem, char *productid);
-#endif
-
-#ifdef CONFIG_ACPI
-
-static inline int es7000_check_dsdt(void)
-{
-	struct acpi_table_header header;
-
-	if (ACPI_SUCCESS(acpi_get_table_header(ACPI_SIG_DSDT, 0, &header)) &&
-	    !strncmp(header.oem_id, "UNISYS", 6))
-		return 1;
-	return 0;
-}
-#endif
-
-#endif /* __ASM_MACH_MPPARSE_H */

arch/x86/include/asm/es7000/wakecpu.h

@@ -1,37 +0,0 @@
-#ifndef __ASM_ES7000_WAKECPU_H
-#define __ASM_ES7000_WAKECPU_H
-
-#define TRAMPOLINE_PHYS_LOW	0x467
-#define TRAMPOLINE_PHYS_HIGH	0x469
-
-static inline void wait_for_init_deassert(atomic_t *deassert)
-{
-#ifndef CONFIG_ES7000_CLUSTERED_APIC
-	while (!atomic_read(deassert))
-		cpu_relax();
-#endif
-	return;
-}
-
-/* Nothing to do for most platforms, since cleared by the INIT cycle */
-static inline void smp_callin_clear_local_apic(void)
-{
-}
-
-static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-extern void __inquire_remote_apic(int apicid);
-
-static inline void inquire_remote_apic(int apicid)
-{
-	if (apic_verbosity >= APIC_DEBUG)
-		__inquire_remote_apic(apicid);
-}
-
-#endif /* __ASM_MACH_WAKECPU_H */

arch/x86/include/asm/fixmap.h

@@ -1,11 +1,145 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ * x86_32 and x86_64 integration by Gustavo F. Padovan, February 2009
+ */
+
 #ifndef _ASM_X86_FIXMAP_H
 #define _ASM_X86_FIXMAP_H
 
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+#include <asm/acpi.h>
+#include <asm/apicdef.h>
+#include <asm/page.h>
+#ifdef CONFIG_X86_32
+#include <linux/threads.h>
+#include <asm/kmap_types.h>
+#else
+#include <asm/vsyscall.h>
+#endif
+
+/*
+ * We can't declare FIXADDR_TOP as variable for x86_64 because vsyscall
+ * uses fixmaps that relies on FIXADDR_TOP for proper address calculation.
+ * Because of this, FIXADDR_TOP x86 integration was left as later work.
+ */
+#ifdef CONFIG_X86_32
+/* used by vmalloc.c, vsyscall.lds.S.
+ *
+ * Leave one empty page between vmalloc'ed areas and
+ * the start of the fixmap.
+ */
+extern unsigned long __FIXADDR_TOP;
+#define FIXADDR_TOP	((unsigned long)__FIXADDR_TOP)
+
+#define FIXADDR_USER_START     __fix_to_virt(FIX_VDSO)
+#define FIXADDR_USER_END       __fix_to_virt(FIX_VDSO - 1)
+#else
+#define FIXADDR_TOP	(VSYSCALL_END-PAGE_SIZE)
+
+/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */
+#define FIXADDR_USER_START	((unsigned long)VSYSCALL32_VSYSCALL)
+#define FIXADDR_USER_END	(FIXADDR_USER_START + PAGE_SIZE)
+#endif
+
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process.
+ * for x86_32: We allocate these special addresses
+ * from the end of virtual memory (0xfffff000) backwards.
+ * Also this lets us do fail-safe vmalloc(), we
+ * can guarantee that these special addresses and
+ * vmalloc()-ed addresses never overlap.
+ *
+ * These 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages (or larger if used with an increment
+ * higher than 1). Use set_fixmap(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+enum fixed_addresses {
 #ifdef CONFIG_X86_32
-# include "fixmap_32.h"
+	FIX_HOLE,
+	FIX_VDSO,
 #else
-# include "fixmap_64.h"
+	VSYSCALL_LAST_PAGE,
+	VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
+			    + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
+	VSYSCALL_HPET,
 #endif
+	FIX_DBGP_BASE,
+	FIX_EARLYCON_MEM_BASE,
+#ifdef CONFIG_X86_LOCAL_APIC
+	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
+#endif
+#ifdef CONFIG_X86_IO_APIC
+	FIX_IO_APIC_BASE_0,
+	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
+#endif
+#ifdef CONFIG_X86_VISWS_APIC
+	FIX_CO_CPU,	/* Cobalt timer */
+	FIX_CO_APIC,	/* Cobalt APIC Redirection Table */
+	FIX_LI_PCIA,	/* Lithium PCI Bridge A */
+	FIX_LI_PCIB,	/* Lithium PCI Bridge B */
+#endif
+#ifdef CONFIG_X86_F00F_BUG
+	FIX_F00F_IDT,	/* Virtual mapping for IDT */
+#endif
+#ifdef CONFIG_X86_CYCLONE_TIMER
+	FIX_CYCLONE_TIMER, /*cyclone timer register*/
+#endif
+#ifdef CONFIG_X86_32
+	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
+	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
+#ifdef CONFIG_PCI_MMCONFIG
+	FIX_PCIE_MCFG,
+#endif
+#endif
+#ifdef CONFIG_PARAVIRT
+	FIX_PARAVIRT_BOOTMAP,
+#endif
+	__end_of_permanent_fixed_addresses,
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+	FIX_OHCI1394_BASE,
+#endif
+	/*
+	 * 256 temporary boot-time mappings, used by early_ioremap(),
+	 * before ioremap() is functional.
+	 *
+	 * We round it up to the next 256 pages boundary so that we
+	 * can have a single pgd entry and a single pte table:
+	 */
+#define NR_FIX_BTMAPS		64
+#define FIX_BTMAPS_SLOTS	4
+	FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
+			(__end_of_permanent_fixed_addresses & 255),
+	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
+#ifdef CONFIG_X86_32
+	FIX_WP_TEST,
+#endif
+	__end_of_fixed_addresses
+};
+
+
+extern void reserve_top_address(unsigned long reserve);
+
+#define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_BOOT_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START		(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_BOOT_START	(FIXADDR_TOP - FIXADDR_BOOT_SIZE)
 
 extern int fixmaps_set;
 
@@ -69,4 +203,5 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr)
 	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
 	return __virt_to_fix(vaddr);
 }
+#endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_FIXMAP_H */

arch/x86/include/asm/fixmap_32.h

@@ -1,119 +0,0 @@
-/*
- * fixmap.h: compile-time virtual memory allocation
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1998 Ingo Molnar
- *
- * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
- */
-
-#ifndef _ASM_X86_FIXMAP_32_H
-#define _ASM_X86_FIXMAP_32_H
-
-
-/* used by vmalloc.c, vsyscall.lds.S.
- *
- * Leave one empty page between vmalloc'ed areas and
- * the start of the fixmap.
- */
-extern unsigned long __FIXADDR_TOP;
-#define FIXADDR_USER_START     __fix_to_virt(FIX_VDSO)
-#define FIXADDR_USER_END       __fix_to_virt(FIX_VDSO - 1)
-
-#ifndef __ASSEMBLY__
-#include <linux/kernel.h>
-#include <asm/acpi.h>
-#include <asm/apicdef.h>
-#include <asm/page.h>
-#include <linux/threads.h>
-#include <asm/kmap_types.h>
-
-/*
- * Here we define all the compile-time 'special' virtual
- * addresses. The point is to have a constant address at
- * compile time, but to set the physical address only
- * in the boot process. We allocate these special addresses
- * from the end of virtual memory (0xfffff000) backwards.
- * Also this lets us do fail-safe vmalloc(), we
- * can guarantee that these special addresses and
- * vmalloc()-ed addresses never overlap.
- *
- * these 'compile-time allocated' memory buffers are
- * fixed-size 4k pages. (or larger if used with an increment
- * highger than 1) use fixmap_set(idx,phys) to associate
- * physical memory with fixmap indices.
- *
- * TLB entries of such buffers will not be flushed across
- * task switches.
- */
-enum fixed_addresses {
-	FIX_HOLE,
-	FIX_VDSO,
-	FIX_DBGP_BASE,
-	FIX_EARLYCON_MEM_BASE,
-#ifdef CONFIG_X86_LOCAL_APIC
-	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
-#endif
-#ifdef CONFIG_X86_IO_APIC
-	FIX_IO_APIC_BASE_0,
-	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1,
-#endif
-#ifdef CONFIG_X86_VISWS_APIC
-	FIX_CO_CPU,	/* Cobalt timer */
-	FIX_CO_APIC,	/* Cobalt APIC Redirection Table */
-	FIX_LI_PCIA,	/* Lithium PCI Bridge A */
-	FIX_LI_PCIB,	/* Lithium PCI Bridge B */
-#endif
-#ifdef CONFIG_X86_F00F_BUG
-	FIX_F00F_IDT,	/* Virtual mapping for IDT */
-#endif
-#ifdef CONFIG_X86_CYCLONE_TIMER
-	FIX_CYCLONE_TIMER, /*cyclone timer register*/
-#endif
-	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
-	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
-#ifdef CONFIG_PCI_MMCONFIG
-	FIX_PCIE_MCFG,
-#endif
-#ifdef CONFIG_PARAVIRT
-	FIX_PARAVIRT_BOOTMAP,
-#endif
-	__end_of_permanent_fixed_addresses,
-	/*
-	 * 256 temporary boot-time mappings, used by early_ioremap(),
-	 * before ioremap() is functional.
-	 *
-	 * We round it up to the next 256 pages boundary so that we
-	 * can have a single pgd entry and a single pte table:
-	 */
-#define NR_FIX_BTMAPS		64
-#define FIX_BTMAPS_SLOTS	4
-	FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
-			(__end_of_permanent_fixed_addresses & 255),
-	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
-	FIX_WP_TEST,
-#ifdef CONFIG_ACPI
-	FIX_ACPI_BEGIN,
-	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
-	FIX_OHCI1394_BASE,
-#endif
-	__end_of_fixed_addresses
-};
-
-extern void reserve_top_address(unsigned long reserve);
-
-
-#define FIXADDR_TOP	((unsigned long)__FIXADDR_TOP)
-
-#define __FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define __FIXADDR_BOOT_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START		(FIXADDR_TOP - __FIXADDR_SIZE)
-#define FIXADDR_BOOT_START	(FIXADDR_TOP - __FIXADDR_BOOT_SIZE)
-
-#endif /* !__ASSEMBLY__ */
-#endif /* _ASM_X86_FIXMAP_32_H */

arch/x86/include/asm/fixmap_64.h

@@ -1,79 +0,0 @@
-/*
- * fixmap.h: compile-time virtual memory allocation
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1998 Ingo Molnar
- */
-
-#ifndef _ASM_X86_FIXMAP_64_H
-#define _ASM_X86_FIXMAP_64_H
-
-#include <linux/kernel.h>
-#include <asm/acpi.h>
-#include <asm/apicdef.h>
-#include <asm/page.h>
-#include <asm/vsyscall.h>
-
-/*
- * Here we define all the compile-time 'special' virtual
- * addresses. The point is to have a constant address at
- * compile time, but to set the physical address only
- * in the boot process.
- *
- * These 'compile-time allocated' memory buffers are
- * fixed-size 4k pages (or larger if used with an increment
- * higher than 1). Use set_fixmap(idx,phys) to associate
- * physical memory with fixmap indices.
- *
- * TLB entries of such buffers will not be flushed across
- * task switches.
- */
-
-enum fixed_addresses {
-	VSYSCALL_LAST_PAGE,
-	VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
-			    + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
-	VSYSCALL_HPET,
-	FIX_DBGP_BASE,
-	FIX_EARLYCON_MEM_BASE,
-	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
-	FIX_IO_APIC_BASE_0,
-	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
-#ifdef CONFIG_PARAVIRT
-	FIX_PARAVIRT_BOOTMAP,
-#endif
-	__end_of_permanent_fixed_addresses,
-#ifdef CONFIG_ACPI
-	FIX_ACPI_BEGIN,
-	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
-	FIX_OHCI1394_BASE,
-#endif
-	/*
-	 * 256 temporary boot-time mappings, used by early_ioremap(),
-	 * before ioremap() is functional.
-	 *
-	 * We round it up to the next 256 pages boundary so that we
-	 * can have a single pgd entry and a single pte table:
-	 */
-#define NR_FIX_BTMAPS		64
-#define FIX_BTMAPS_SLOTS	4
-	FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
-			(__end_of_permanent_fixed_addresses & 255),
-	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
-	__end_of_fixed_addresses
-};
-
-#define FIXADDR_TOP	(VSYSCALL_END-PAGE_SIZE)
-#define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
-
-/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */
-#define FIXADDR_USER_START	((unsigned long)VSYSCALL32_VSYSCALL)
-#define FIXADDR_USER_END	(FIXADDR_USER_START + PAGE_SIZE)
-
-#endif /* _ASM_X86_FIXMAP_64_H */

arch/x86/include/asm/genapic.h

@@ -1,5 +1 @@
-#ifdef CONFIG_X86_32
-# include "genapic_32.h"
-#else
-# include "genapic_64.h"
-#endif
+#include <asm/apic.h>

arch/x86/include/asm/genapic_32.h

@@ -1,148 +0,0 @@
-#ifndef _ASM_X86_GENAPIC_32_H
-#define _ASM_X86_GENAPIC_32_H
-
-#include <asm/mpspec.h>
-#include <asm/atomic.h>
-
-/*
- * Generic APIC driver interface.
- *
- * An straight forward mapping of the APIC related parts of the
- * x86 subarchitecture interface to a dynamic object.
- *
- * This is used by the "generic" x86 subarchitecture.
- *
- * Copyright 2003 Andi Kleen, SuSE Labs.
- */
-
-struct mpc_bus;
-struct mpc_table;
-struct mpc_cpu;
-
-struct genapic {
-	char *name;
-	int (*probe)(void);
-
-	int (*apic_id_registered)(void);
-	const struct cpumask *(*target_cpus)(void);
-	int int_delivery_mode;
-	int int_dest_mode;
-	int ESR_DISABLE;
-	int apic_destination_logical;
-	unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid);
-	unsigned long (*check_apicid_present)(int apicid);
-	int no_balance_irq;
-	int no_ioapic_check;
-	void (*init_apic_ldr)(void);
-	physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map);
-
-	void (*setup_apic_routing)(void);
-	int (*multi_timer_check)(int apic, int irq);
-	int (*apicid_to_node)(int logical_apicid);
-	int (*cpu_to_logical_apicid)(int cpu);
-	int (*cpu_present_to_apicid)(int mps_cpu);
-	physid_mask_t (*apicid_to_cpu_present)(int phys_apicid);
-	void (*setup_portio_remap)(void);
-	int (*check_phys_apicid_present)(int boot_cpu_physical_apicid);
-	void (*enable_apic_mode)(void);
-	u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb);
-
-	/* mpparse */
-	/* When one of the next two hooks returns 1 the genapic
-	   is switched to this. Essentially they are additional probe
-	   functions. */
-	int (*mps_oem_check)(struct mpc_table *mpc, char *oem,
-			     char *productid);
-	int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
-
-	unsigned (*get_apic_id)(unsigned long x);
-	unsigned long apic_id_mask;
-	unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
-	unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
-					       const struct cpumask *andmask);
-	void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
-
-#ifdef CONFIG_SMP
-	/* ipi */
-	void (*send_IPI_mask)(const struct cpumask *mask, int vector);
-	void (*send_IPI_mask_allbutself)(const struct cpumask *mask,
-					 int vector);
-	void (*send_IPI_allbutself)(int vector);
-	void (*send_IPI_all)(int vector);
-#endif
-	int (*wakeup_cpu)(int apicid, unsigned long start_eip);
-	int trampoline_phys_low;
-	int trampoline_phys_high;
-	void (*wait_for_init_deassert)(atomic_t *deassert);
-	void (*smp_callin_clear_local_apic)(void);
-	void (*store_NMI_vector)(unsigned short *high, unsigned short *low);
-	void (*restore_NMI_vector)(unsigned short *high, unsigned short *low);
-	void (*inquire_remote_apic)(int apicid);
-};
-
-#define APICFUNC(x) .x = x,
-
-/* More functions could be probably marked IPIFUNC and save some space
-   in UP GENERICARCH kernels, but I don't have the nerve right now
-   to untangle this mess. -AK  */
-#ifdef CONFIG_SMP
-#define IPIFUNC(x) APICFUNC(x)
-#else
-#define IPIFUNC(x)
-#endif
-
-#define APIC_INIT(aname, aprobe)			\
-{							\
-	.name = aname,					\
-	.probe = aprobe,				\
-	.int_delivery_mode = INT_DELIVERY_MODE,		\
-	.int_dest_mode = INT_DEST_MODE,			\
-	.no_balance_irq = NO_BALANCE_IRQ,		\
-	.ESR_DISABLE = esr_disable,			\
-	.apic_destination_logical = APIC_DEST_LOGICAL,	\
-	APICFUNC(apic_id_registered)			\
-	APICFUNC(target_cpus)				\
-	APICFUNC(check_apicid_used)			\
-	APICFUNC(check_apicid_present)			\
-	APICFUNC(init_apic_ldr)				\
-	APICFUNC(ioapic_phys_id_map)			\
-	APICFUNC(setup_apic_routing)			\
-	APICFUNC(multi_timer_check)			\
-	APICFUNC(apicid_to_node)			\
-	APICFUNC(cpu_to_logical_apicid)			\
-	APICFUNC(cpu_present_to_apicid)			\
-	APICFUNC(apicid_to_cpu_present)			\
-	APICFUNC(setup_portio_remap)			\
-	APICFUNC(check_phys_apicid_present)		\
-	APICFUNC(mps_oem_check)				\
-	APICFUNC(get_apic_id)				\
-	.apic_id_mask = APIC_ID_MASK,			\
-	APICFUNC(cpu_mask_to_apicid)			\
-	APICFUNC(cpu_mask_to_apicid_and)		\
-	APICFUNC(vector_allocation_domain)		\
-	APICFUNC(acpi_madt_oem_check)			\
-	IPIFUNC(send_IPI_mask)				\
-	IPIFUNC(send_IPI_allbutself)			\
-	IPIFUNC(send_IPI_all)				\
-	APICFUNC(enable_apic_mode)			\
-	APICFUNC(phys_pkg_id)				\
-	.trampoline_phys_low = TRAMPOLINE_PHYS_LOW,		\
-	.trampoline_phys_high = TRAMPOLINE_PHYS_HIGH,		\
-	APICFUNC(wait_for_init_deassert)		\
-	APICFUNC(smp_callin_clear_local_apic)		\
-	APICFUNC(store_NMI_vector)			\
-	APICFUNC(restore_NMI_vector)			\
-	APICFUNC(inquire_remote_apic)			\
-}
-
-extern struct genapic *genapic;
-extern void es7000_update_genapic_to_cluster(void);
-
-enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
-#define get_uv_system_type()		UV_NONE
-#define is_uv_system()			0
-#define uv_wakeup_secondary(a, b)	1
-#define uv_system_init()		do {} while (0)
-
-
-#endif /* _ASM_X86_GENAPIC_32_H */

arch/x86/include/asm/genapic_64.h

@@ -1,66 +0,0 @@
-#ifndef _ASM_X86_GENAPIC_64_H
-#define _ASM_X86_GENAPIC_64_H
-
-#include <linux/cpumask.h>
-
-/*
- * Copyright 2004 James Cleverdon, IBM.
- * Subject to the GNU Public License, v.2
- *
- * Generic APIC sub-arch data struct.
- *
- * Hacked for x86-64 by James Cleverdon from i386 architecture code by
- * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
- * James Cleverdon.
- */
-
-struct genapic {
-	char *name;
-	int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
-	u32 int_delivery_mode;
-	u32 int_dest_mode;
-	int (*apic_id_registered)(void);
-	const struct cpumask *(*target_cpus)(void);
-	void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
-	void (*init_apic_ldr)(void);
-	/* ipi */
-	void (*send_IPI_mask)(const struct cpumask *mask, int vector);
-	void (*send_IPI_mask_allbutself)(const struct cpumask *mask,
-					 int vector);
-	void (*send_IPI_allbutself)(int vector);
-	void (*send_IPI_all)(int vector);
-	void (*send_IPI_self)(int vector);
-	/* */
-	unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
-	unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
-					       const struct cpumask *andmask);
-	unsigned int (*phys_pkg_id)(int index_msb);
-	unsigned int (*get_apic_id)(unsigned long x);
-	unsigned long (*set_apic_id)(unsigned int id);
-	unsigned long apic_id_mask;
-	/* wakeup_secondary_cpu */
-	int (*wakeup_cpu)(int apicid, unsigned long start_eip);
-};
-
-extern struct genapic *genapic;
-
-extern struct genapic apic_flat;
-extern struct genapic apic_physflat;
-extern struct genapic apic_x2apic_cluster;
-extern struct genapic apic_x2apic_phys;
-extern int acpi_madt_oem_check(char *, char *);
-
-extern void apic_send_IPI_self(int vector);
-enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
-extern enum uv_system_type get_uv_system_type(void);
-extern int is_uv_system(void);
-
-extern struct genapic apic_x2apic_uv_x;
-DECLARE_PER_CPU(int, x2apic_extra_bits);
-extern void uv_cpu_init(void);
-extern void uv_system_init(void);
-extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
-
-extern void setup_apic_routing(void);
-
-#endif /* _ASM_X86_GENAPIC_64_H */

arch/x86/include/asm/hardirq.h

@@ -1,11 +1,52 @@
-#ifdef CONFIG_X86_32
-# include "hardirq_32.h"
-#else
-# include "hardirq_64.h"
+#ifndef _ASM_X86_HARDIRQ_H
+#define _ASM_X86_HARDIRQ_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+typedef struct {
+	unsigned int __softirq_pending;
+	unsigned int __nmi_count;	/* arch dependent */
+	unsigned int irq0_irqs;
+#ifdef CONFIG_X86_LOCAL_APIC
+	unsigned int apic_timer_irqs;	/* arch dependent */
+	unsigned int irq_spurious_count;
+#endif
+#ifdef CONFIG_SMP
+	unsigned int irq_resched_count;
+	unsigned int irq_call_count;
+	unsigned int irq_tlb_count;
+#endif
+#ifdef CONFIG_X86_MCE
+	unsigned int irq_thermal_count;
+# ifdef CONFIG_X86_64
+	unsigned int irq_threshold_count;
+# endif
 #endif
+} ____cacheline_aligned irq_cpustat_t;
+
+DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
+
+/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
+#define MAX_HARDIRQS_PER_CPU NR_VECTORS
+
+#define __ARCH_IRQ_STAT
+
+#define inc_irq_stat(member)	percpu_add(irq_stat.member, 1)
+
+#define local_softirq_pending()	percpu_read(irq_stat.__softirq_pending)
+
+#define __ARCH_SET_SOFTIRQ_PENDING
+
+#define set_softirq_pending(x)	percpu_write(irq_stat.__softirq_pending, (x))
+#define or_softirq_pending(x)	percpu_or(irq_stat.__softirq_pending, (x))
+
+extern void ack_bad_irq(unsigned int irq);
 
 extern u64 arch_irq_stat_cpu(unsigned int cpu);
 #define arch_irq_stat_cpu	arch_irq_stat_cpu
 
 extern u64 arch_irq_stat(void);
 #define arch_irq_stat		arch_irq_stat
+
+#endif /* _ASM_X86_HARDIRQ_H */

arch/x86/include/asm/hardirq_32.h

@@ -1,30 +0,0 @@
-#ifndef _ASM_X86_HARDIRQ_32_H
-#define _ASM_X86_HARDIRQ_32_H
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-
-typedef struct {
-	unsigned int __softirq_pending;
-	unsigned long idle_timestamp;
-	unsigned int __nmi_count;	/* arch dependent */
-	unsigned int apic_timer_irqs;	/* arch dependent */
-	unsigned int irq0_irqs;
-	unsigned int irq_resched_count;
-	unsigned int irq_call_count;
-	unsigned int irq_tlb_count;
-	unsigned int irq_thermal_count;
-	unsigned int irq_spurious_count;
-} ____cacheline_aligned irq_cpustat_t;
-
-DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
-
-#define __ARCH_IRQ_STAT
-#define __IRQ_STAT(cpu, member) (per_cpu(irq_stat, cpu).member)
-
-#define inc_irq_stat(member)	(__get_cpu_var(irq_stat).member++)
-
-void ack_bad_irq(unsigned int irq);
-#include <linux/irq_cpustat.h>
-
-#endif /* _ASM_X86_HARDIRQ_32_H */

arch/x86/include/asm/hardirq_64.h

@@ -1,25 +0,0 @@
-#ifndef _ASM_X86_HARDIRQ_64_H
-#define _ASM_X86_HARDIRQ_64_H
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-#include <asm/pda.h>
-#include <asm/apic.h>
-
-/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
-#define MAX_HARDIRQS_PER_CPU NR_VECTORS
-
-#define __ARCH_IRQ_STAT 1
-
-#define inc_irq_stat(member)	add_pda(member, 1)
-
-#define local_softirq_pending() read_pda(__softirq_pending)
-
-#define __ARCH_SET_SOFTIRQ_PENDING 1
-
-#define set_softirq_pending(x) write_pda(__softirq_pending, (x))
-#define or_softirq_pending(x)  or_pda(__softirq_pending, (x))
-
-extern void ack_bad_irq(unsigned int irq);
-
-#endif /* _ASM_X86_HARDIRQ_64_H */

arch/x86/include/asm/hw_irq.h

@@ -25,8 +25,6 @@
 #include <asm/irq.h>
 #include <asm/sections.h>
 
-#define platform_legacy_irq(irq)	((irq) < 16)
-
 /* Interrupt handlers registered during init_IRQ */
 extern void apic_timer_interrupt(void);
 extern void error_interrupt(void);
@@ -58,7 +56,7 @@ extern void make_8259A_irq(unsigned int irq);
 extern void init_8259A(int aeoi);
 
 /* IOAPIC */
-#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
+#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1<<(x)) & io_apic_irqs))
 extern unsigned long io_apic_irqs;
 
 extern void init_VISWS_APIC_irqs(void);
@@ -67,15 +65,7 @@ extern void disable_IO_APIC(void);
 extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
 extern void setup_ioapic_dest(void);
 
-#ifdef CONFIG_X86_64
 extern void enable_IO_APIC(void);
-#endif
-
-/* IPI functions */
-#ifdef CONFIG_X86_32
-extern void send_IPI_self(int vector);
-#endif
-extern void send_IPI(int dest, int vector);
 
 /* Statistics */
 extern atomic_t irq_err_count;
@@ -84,21 +74,11 @@ extern atomic_t irq_mis_count;
 /* EISA */
 extern void eisa_set_level_irq(unsigned int irq);
 
-/* Voyager functions */
-extern asmlinkage void vic_cpi_interrupt(void);
-extern asmlinkage void vic_sys_interrupt(void);
-extern asmlinkage void vic_cmn_interrupt(void);
-extern asmlinkage void qic_timer_interrupt(void);
-extern asmlinkage void qic_invalidate_interrupt(void);
-extern asmlinkage void qic_reschedule_interrupt(void);
-extern asmlinkage void qic_enable_irq_interrupt(void);
-extern asmlinkage void qic_call_function_interrupt(void);
-
 /* SMP */
 extern void smp_apic_timer_interrupt(struct pt_regs *);
 extern void smp_spurious_interrupt(struct pt_regs *);
 extern void smp_error_interrupt(struct pt_regs *);
-#ifdef CONFIG_X86_SMP
+#ifdef CONFIG_SMP
 extern void smp_reschedule_interrupt(struct pt_regs *);
 extern void smp_call_function_interrupt(struct pt_regs *);
 extern void smp_call_function_single_interrupt(struct pt_regs *);

arch/x86/include/asm/i8259.h

@@ -60,4 +60,8 @@ extern struct irq_chip i8259A_chip;
 extern void mask_8259A(void);
 extern void unmask_8259A(void);
 
+#ifdef CONFIG_X86_32
+extern void init_ISA_irqs(void);
+#endif
+
 #endif /* _ASM_X86_I8259_H */

arch/x86/include/asm/io.h

@@ -5,6 +5,7 @@
 
 #include <linux/compiler.h>
 #include <asm-generic/int-ll64.h>
+#include <asm/page.h>
 
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
@@ -80,6 +81,98 @@ static inline void writeq(__u64 val, volatile void __iomem *addr)
 #define readq			readq
 #define writeq			writeq
 
+/**
+ *	virt_to_phys	-	map virtual addresses to physical
+ *	@address: address to remap
+ *
+ *	The returned physical address is the physical (CPU) mapping for
+ *	the memory address given. It is only valid to use this function on
+ *	addresses directly mapped or allocated via kmalloc.
+ *
+ *	This function does not give bus mappings for DMA transfers. In
+ *	almost all conceivable cases a device driver should not be using
+ *	this function
+ */
+
+static inline phys_addr_t virt_to_phys(volatile void *address)
+{
+	return __pa(address);
+}
+
+/**
+ *	phys_to_virt	-	map physical address to virtual
+ *	@address: address to remap
+ *
+ *	The returned virtual address is a current CPU mapping for
+ *	the memory address given. It is only valid to use this function on
+ *	addresses that have a kernel mapping
+ *
+ *	This function does not handle bus mappings for DMA transfers. In
+ *	almost all conceivable cases a device driver should not be using
+ *	this function
+ */
+
+static inline void *phys_to_virt(phys_addr_t address)
+{
+	return __va(address);
+}
+
+/*
+ * Change "struct page" to physical address.
+ */
+#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+
+/*
+ * ISA I/O bus memory addresses are 1:1 with the physical address.
+ * However, we truncate the address to unsigned int to avoid undesirable
+ * promitions in legacy drivers.
+ */
+static inline unsigned int isa_virt_to_bus(volatile void *address)
+{
+	return (unsigned int)virt_to_phys(address);
+}
+#define isa_page_to_bus(page)	((unsigned int)page_to_phys(page))
+#define isa_bus_to_virt		phys_to_virt
+
+/*
+ * However PCI ones are not necessarily 1:1 and therefore these interfaces
+ * are forbidden in portable PCI drivers.
+ *
+ * Allow them on x86 for legacy drivers, though.
+ */
+#define virt_to_bus virt_to_phys
+#define bus_to_virt phys_to_virt
+
+/**
+ * ioremap     -   map bus memory into CPU space
+ * @offset:    bus address of the memory
+ * @size:      size of the resource to map
+ *
+ * ioremap performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * If the area you are trying to map is a PCI BAR you should have a
+ * look at pci_iomap().
+ */
+extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
+				unsigned long prot_val);
+
+/*
+ * The default ioremap() behavior is non-cached:
+ */
+static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
+{
+	return ioremap_nocache(offset, size);
+}
+
+extern void iounmap(volatile void __iomem *addr);
+
+
 #ifdef CONFIG_X86_32
 # include "io_32.h"
 #else
@@ -91,7 +184,7 @@ extern void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
 
 extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 				unsigned long prot_val);
-extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size);
+extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size);
 
 /*
  * early_ioremap() and early_iounmap() are for temporary early boot-time
@@ -103,7 +196,7 @@ extern void early_ioremap_reset(void);
 extern void __iomem *early_ioremap(unsigned long offset, unsigned long size);
 extern void __iomem *early_memremap(unsigned long offset, unsigned long size);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
-extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
 
+#define IO_SPACE_LIMIT 0xffff
 
 #endif /* _ASM_X86_IO_H */

arch/x86/include/asm/io_32.h

@@ -37,8 +37,6 @@
   *  - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
   */
 
-#define IO_SPACE_LIMIT 0xffff
-
 #define XQUAD_PORTIO_BASE 0xfe400000
 #define XQUAD_PORTIO_QUAD 0x40000  /* 256k per quad. */
 
@@ -53,92 +51,6 @@
  */
 #define xlate_dev_kmem_ptr(p)	p
 
-/**
- *	virt_to_phys	-	map virtual addresses to physical
- *	@address: address to remap
- *
- *	The returned physical address is the physical (CPU) mapping for
- *	the memory address given. It is only valid to use this function on
- *	addresses directly mapped or allocated via kmalloc.
- *
- *	This function does not give bus mappings for DMA transfers. In
- *	almost all conceivable cases a device driver should not be using
- *	this function
- */
-
-static inline unsigned long virt_to_phys(volatile void *address)
-{
-	return __pa(address);
-}
-
-/**
- *	phys_to_virt	-	map physical address to virtual
- *	@address: address to remap
- *
- *	The returned virtual address is a current CPU mapping for
- *	the memory address given. It is only valid to use this function on
- *	addresses that have a kernel mapping
- *
- *	This function does not handle bus mappings for DMA transfers. In
- *	almost all conceivable cases a device driver should not be using
- *	this function
- */
-
-static inline void *phys_to_virt(unsigned long address)
-{
-	return __va(address);
-}
-
-/*
- * Change "struct page" to physical address.
- */
-#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
-
-/**
- * ioremap     -   map bus memory into CPU space
- * @offset:    bus address of the memory
- * @size:      size of the resource to map
- *
- * ioremap performs a platform specific sequence of operations to
- * make bus memory CPU accessible via the readb/readw/readl/writeb/
- * writew/writel functions and the other mmio helpers. The returned
- * address is not guaranteed to be usable directly as a virtual
- * address.
- *
- * If the area you are trying to map is a PCI BAR you should have a
- * look at pci_iomap().
- */
-extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
-				unsigned long prot_val);
-
-/*
- * The default ioremap() behavior is non-cached:
- */
-static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
-{
-	return ioremap_nocache(offset, size);
-}
-
-extern void iounmap(volatile void __iomem *addr);
-
-/*
- * ISA I/O bus memory addresses are 1:1 with the physical address.
- */
-#define isa_virt_to_bus virt_to_phys
-#define isa_page_to_bus page_to_phys
-#define isa_bus_to_virt phys_to_virt
-
-/*
- * However PCI ones are not necessarily 1:1 and therefore these interfaces
- * are forbidden in portable PCI drivers.
- *
- * Allow them on x86 for legacy drivers, though.
- */
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-
 static inline void
 memset_io(volatile void __iomem *addr, unsigned char val, int count)
 {

arch/x86/include/asm/io_64.h

@@ -136,73 +136,12 @@ __OUTS(b)
 __OUTS(w)
 __OUTS(l)
 
-#define IO_SPACE_LIMIT 0xffff
-
 #if defined(__KERNEL__) && defined(__x86_64__)
 
 #include <linux/vmalloc.h>
 
-#ifndef __i386__
-/*
- * Change virtual addresses to physical addresses and vv.
- * These are pretty trivial
- */
-static inline unsigned long virt_to_phys(volatile void *address)
-{
-	return __pa(address);
-}
-
-static inline void *phys_to_virt(unsigned long address)
-{
-	return __va(address);
-}
-#endif
-
-/*
- * Change "struct page" to physical address.
- */
-#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
-
 #include <asm-generic/iomap.h>
 
-/*
- * This one maps high address device memory and turns off caching for that area.
- * it's useful if some control registers are in such an area and write combining
- * or read caching is not desirable:
- */
-extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
-				unsigned long prot_val);
-
-/*
- * The default ioremap() behavior is non-cached:
- */
-static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
-{
-	return ioremap_nocache(offset, size);
-}
-
-extern void iounmap(volatile void __iomem *addr);
-
-extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
-
-/*
- * ISA I/O bus memory addresses are 1:1 with the physical address.
- */
-#define isa_virt_to_bus virt_to_phys
-#define isa_page_to_bus page_to_phys
-#define isa_bus_to_virt phys_to_virt
-
-/*
- * However PCI ones are not necessarily 1:1 and therefore these interfaces
- * are forbidden in portable PCI drivers.
- *
- * Allow them on x86 for legacy drivers, though.
- */
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-
 void __memcpy_fromio(void *, unsigned long, unsigned);
 void __memcpy_toio(unsigned long, const void *, unsigned);
 

arch/x86/include/asm/io_apic.h

@@ -114,38 +114,16 @@ struct IR_IO_APIC_route_entry {
 extern int nr_ioapics;
 extern int nr_ioapic_registers[MAX_IO_APICS];
 
-/*
- * MP-BIOS irq configuration table structures:
- */
-
 #define MP_MAX_IOAPIC_PIN 127
 
-struct mp_config_ioapic {
-	unsigned long mp_apicaddr;
-	unsigned int mp_apicid;
-	unsigned char mp_type;
-	unsigned char mp_apicver;
-	unsigned char mp_flags;
-};
-
-struct mp_config_intsrc {
-	unsigned int mp_dstapic;
-	unsigned char mp_type;
-	unsigned char mp_irqtype;
-	unsigned short mp_irqflag;
-	unsigned char mp_srcbus;
-	unsigned char mp_srcbusirq;
-	unsigned char mp_dstirq;
-};
-
 /* I/O APIC entries */
-extern struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
+extern struct mpc_ioapic mp_ioapics[MAX_IO_APICS];
 
 /* # of MP IRQ source entries */
 extern int mp_irq_entries;
 
 /* MP IRQ source entries */
-extern struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
 
 /* non-0 if default (table-less) MP configuration */
 extern int mpc_default_type;
@@ -165,15 +143,6 @@ extern int noioapicreroute;
 /* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
 extern int timer_through_8259;
 
-static inline void disable_ioapic_setup(void)
-{
-#ifdef CONFIG_PCI
-	noioapicquirk = 1;
-	noioapicreroute = -1;
-#endif
-	skip_ioapic_setup = 1;
-}
-
 /*
  * If we use the IO-APIC for IRQ routing, disable automatic
  * assignment of PCI IRQ's.
@@ -200,6 +169,12 @@ extern void reinit_intr_remapped_IO_APIC(int);
 
 extern void probe_nr_irqs_gsi(void);
 
+extern int setup_ioapic_entry(int apic, int irq,
+			      struct IO_APIC_route_entry *entry,
+			      unsigned int destination, int trigger,
+			      int polarity, int vector);
+extern void ioapic_write_entry(int apic, int pin,
+			       struct IO_APIC_route_entry e);
 #else  /* !CONFIG_X86_IO_APIC */
 #define io_apic_assign_pci_irqs 0
 static const int timer_through_8259 = 0;

arch/x86/include/asm/ipi.h

@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_IPI_H
 #define _ASM_X86_IPI_H
 
+#ifdef CONFIG_X86_LOCAL_APIC
+
 /*
  * Copyright 2004 James Cleverdon, IBM.
  * Subject to the GNU Public License, v.2
@@ -55,8 +57,8 @@ static inline void __xapic_wait_icr_idle(void)
 		cpu_relax();
 }
 
-static inline void __send_IPI_shortcut(unsigned int shortcut, int vector,
-				       unsigned int dest)
+static inline void
+__default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest)
 {
 	/*
 	 * Subtle. In the case of the 'never do double writes' workaround
@@ -87,8 +89,8 @@ static inline void __send_IPI_shortcut(unsigned int shortcut, int vector,
  * This is used to send an IPI with no shorthand notation (the destination is
  * specified in bits 56 to 63 of the ICR).
  */
-static inline void __send_IPI_dest_field(unsigned int mask, int vector,
-					 unsigned int dest)
+static inline void
+ __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest)
 {
 	unsigned long cfg;
 
@@ -117,41 +119,44 @@ static inline void __send_IPI_dest_field(unsigned int mask, int vector,
 	native_apic_mem_write(APIC_ICR, cfg);
 }
 
-static inline void send_IPI_mask_sequence(const struct cpumask *mask,
-					  int vector)
-{
-	unsigned long flags;
-	unsigned long query_cpu;
+extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask,
+						 int vector);
+extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
+							 int vector);
+extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
+							 int vector);
+extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
+							 int vector);
 
-	/*
-	 * Hack. The clustered APIC addressing mode doesn't allow us to send
-	 * to an arbitrary mask, so I do a unicast to each CPU instead.
-	 * - mbligh
-	 */
-	local_irq_save(flags);
-	for_each_cpu(query_cpu, mask) {
-		__send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, query_cpu),
-				      vector, APIC_DEST_PHYSICAL);
-	}
-	local_irq_restore(flags);
+/* Avoid include hell */
+#define NMI_VECTOR 0x02
+
+extern int no_broadcast;
+
+static inline void __default_local_send_IPI_allbutself(int vector)
+{
+	if (no_broadcast || vector == NMI_VECTOR)
+		apic->send_IPI_mask_allbutself(cpu_online_mask, vector);
+	else
+		__default_send_IPI_shortcut(APIC_DEST_ALLBUT, vector, apic->dest_logical);
 }
 
-static inline void send_IPI_mask_allbutself(const struct cpumask *mask,
-					    int vector)
+static inline void __default_local_send_IPI_all(int vector)
 {
-	unsigned long flags;
-	unsigned int query_cpu;
-	unsigned int this_cpu = smp_processor_id();
-
-	/* See Hack comment above */
-
-	local_irq_save(flags);
-	for_each_cpu(query_cpu, mask)
-		if (query_cpu != this_cpu)
-			__send_IPI_dest_field(
-				per_cpu(x86_cpu_to_apicid, query_cpu),
-				vector, APIC_DEST_PHYSICAL);
-	local_irq_restore(flags);
+	if (no_broadcast || vector == NMI_VECTOR)
+		apic->send_IPI_mask(cpu_online_mask, vector);
+	else
+		__default_send_IPI_shortcut(APIC_DEST_ALLINC, vector, apic->dest_logical);
 }
 
+#ifdef CONFIG_X86_32
+extern void default_send_IPI_mask_logical(const struct cpumask *mask,
+						 int vector);
+extern void default_send_IPI_allbutself(int vector);
+extern void default_send_IPI_all(int vector);
+extern void default_send_IPI_self(int vector);
+#endif
+
+#endif
+
 #endif /* _ASM_X86_IPI_H */

arch/x86/include/asm/irq.h

@@ -36,9 +36,11 @@ static inline int irq_canonicalize(int irq)
 extern void fixup_irqs(void);
 #endif
 
-extern unsigned int do_IRQ(struct pt_regs *regs);
 extern void init_IRQ(void);
 extern void native_init_IRQ(void);
+extern bool handle_irq(unsigned irq, struct pt_regs *regs);
+
+extern unsigned int do_IRQ(struct pt_regs *regs);
 
 /* Interrupt vector management */
 extern DECLARE_BITMAP(used_vectors, NR_VECTORS);

arch/x86/include/asm/irq_regs.h

@@ -1,5 +1,31 @@
-#ifdef CONFIG_X86_32
-# include "irq_regs_32.h"
-#else
-# include "irq_regs_64.h"
-#endif
+/*
+ * Per-cpu current frame pointer - the location of the last exception frame on
+ * the stack, stored in the per-cpu area.
+ *
+ * Jeremy Fitzhardinge <jeremy@goop.org>
+ */
+#ifndef _ASM_X86_IRQ_REGS_H
+#define _ASM_X86_IRQ_REGS_H
+
+#include <asm/percpu.h>
+
+#define ARCH_HAS_OWN_IRQ_REGS
+
+DECLARE_PER_CPU(struct pt_regs *, irq_regs);
+
+static inline struct pt_regs *get_irq_regs(void)
+{
+	return percpu_read(irq_regs);
+}
+
+static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
+{
+	struct pt_regs *old_regs;
+
+	old_regs = get_irq_regs();
+	percpu_write(irq_regs, new_regs);
+
+	return old_regs;
+}
+
+#endif /* _ASM_X86_IRQ_REGS_32_H */

arch/x86/include/asm/irq_regs_32.h

@@ -1,31 +0,0 @@
-/*
- * Per-cpu current frame pointer - the location of the last exception frame on
- * the stack, stored in the per-cpu area.
- *
- * Jeremy Fitzhardinge <jeremy@goop.org>
- */
-#ifndef _ASM_X86_IRQ_REGS_32_H
-#define _ASM_X86_IRQ_REGS_32_H
-
-#include <asm/percpu.h>
-
-#define ARCH_HAS_OWN_IRQ_REGS
-
-DECLARE_PER_CPU(struct pt_regs *, irq_regs);
-
-static inline struct pt_regs *get_irq_regs(void)
-{
-	return x86_read_percpu(irq_regs);
-}
-
-static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
-{
-	struct pt_regs *old_regs;
-
-	old_regs = get_irq_regs();
-	x86_write_percpu(irq_regs, new_regs);
-
-	return old_regs;
-}
-
-#endif /* _ASM_X86_IRQ_REGS_32_H */