Merge branch 'percpu-for-linus' into percpu-for-next

Conflicts:
	arch/sparc/kernel/smp_64.c
	arch/x86/kernel/cpu/perf_counter.c
	arch/x86/kernel/setup_percpu.c
	drivers/cpufreq/cpufreq_ondemand.c
	mm/percpu.c

Conflicts in core and arch percpu codes are mostly from commit
ed78e1e078dd44249f88b1dd8c76dafb39567161 which substituted many
num_possible_cpus() with nr_cpu_ids.  As for-next branch has moved all
the first chunk allocators into mm/percpu.c, the changes are moved
from arch code to mm/percpu.c.

Signed-off-by: Tejun Heo <tj@kernel.org>

arch/ia64/Makefile

@@ -41,11 +41,6 @@ $(error Sorry, you need a newer version of the assember, one that is built from
 		ftp://ftp.hpl.hp.com/pub/linux-ia64/gas-030124.tar.gz)
 endif
 
-ifeq ($(call cc-version),0304)
-	cflags-$(CONFIG_ITANIUM)	+= -mtune=merced
-	cflags-$(CONFIG_MCKINLEY)	+= -mtune=mckinley
-endif
-
 KBUILD_CFLAGS += $(cflags-y)
 head-y := arch/ia64/kernel/head.o arch/ia64/kernel/init_task.o
 

arch/ia64/include/asm/bitops.h

@@ -286,7 +286,7 @@ __test_and_clear_bit(int nr, volatile void * addr)
 {
 	__u32 *p = (__u32 *) addr + (nr >> 5);
 	__u32 m = 1 << (nr & 31);
-	int oldbitset = *p & m;
+	int oldbitset = (*p & m) != 0;
 
 	*p &= ~m;
 	return oldbitset;

arch/ia64/include/asm/fpu.h

@@ -6,6 +6,8 @@
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  */
 
+#include <linux/types.h>
+
 /* floating point status register: */
 #define FPSR_TRAP_VD	(1 << 0)	/* invalid op trap disabled */
 #define FPSR_TRAP_DD	(1 << 1)	/* denormal trap disabled */

arch/ia64/include/asm/pgalloc.h

@@ -48,7 +48,7 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 {
 	quicklist_free(0, NULL, pud);
 }
-#define __pud_free_tlb(tlb, pud)	pud_free((tlb)->mm, pud)
+#define __pud_free_tlb(tlb, pud, address)	pud_free((tlb)->mm, pud)
 #endif /* CONFIG_PGTABLE_4 */
 
 static inline void
@@ -67,7 +67,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 	quicklist_free(0, NULL, pmd);
 }
 
-#define __pmd_free_tlb(tlb, pmd)	pmd_free((tlb)->mm, pmd)
+#define __pmd_free_tlb(tlb, pmd, address)	pmd_free((tlb)->mm, pmd)
 
 static inline void
 pmd_populate(struct mm_struct *mm, pmd_t * pmd_entry, pgtable_t pte)
@@ -117,6 +117,6 @@ static inline void check_pgt_cache(void)
 	quicklist_trim(0, NULL, 25, 16);
 }
 
-#define __pte_free_tlb(tlb, pte)	pte_free((tlb)->mm, pte)
+#define __pte_free_tlb(tlb, pte, address)	pte_free((tlb)->mm, pte)
 
 #endif				/* _ASM_IA64_PGALLOC_H */

arch/ia64/include/asm/pgtable.h

@@ -155,7 +155,6 @@
 #include <linux/bitops.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
-#include <asm/processor.h>
 
 /*
  * Next come the mappings that determine how mmap() protection bits

arch/ia64/include/asm/thread_info.h

@@ -48,7 +48,7 @@ struct thread_info {
 	.flags		= 0,			\
 	.cpu		= 0,			\
 	.addr_limit	= KERNEL_DS,		\
-	.preempt_count	= 0,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
 	},					\

arch/ia64/include/asm/tlb.h

@@ -236,22 +236,22 @@ do {							\
 	__tlb_remove_tlb_entry(tlb, ptep, addr);	\
 } while (0)
 
-#define pte_free_tlb(tlb, ptep)				\
+#define pte_free_tlb(tlb, ptep, address)		\
 do {							\
 	tlb->need_flush = 1;				\
-	__pte_free_tlb(tlb, ptep);			\
+	__pte_free_tlb(tlb, ptep, address);		\
 } while (0)
 
-#define pmd_free_tlb(tlb, ptep)				\
+#define pmd_free_tlb(tlb, ptep, address)		\
 do {							\
 	tlb->need_flush = 1;				\
-	__pmd_free_tlb(tlb, ptep);			\
+	__pmd_free_tlb(tlb, ptep, address);		\
 } while (0)
 
-#define pud_free_tlb(tlb, pudp)				\
+#define pud_free_tlb(tlb, pudp, address)		\
 do {							\
 	tlb->need_flush = 1;				\
-	__pud_free_tlb(tlb, pudp);			\
+	__pud_free_tlb(tlb, pudp, address);		\
 } while (0)
 
 #endif /* _ASM_IA64_TLB_H */

arch/ia64/include/asm/xen/hypervisor.h

@@ -33,6 +33,7 @@
 #ifndef _ASM_IA64_XEN_HYPERVISOR_H
 #define _ASM_IA64_XEN_HYPERVISOR_H
 
+#include <linux/err.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/version.h>	/* to compile feature.c */
 #include <xen/features.h>		/* to comiple xen-netfront.c */

arch/ia64/kernel/dma-mapping.c

@@ -6,6 +6,14 @@ int iommu_detected __read_mostly;
 struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
+#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
+
+static int __init dma_init(void)
+{
+       dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+}
+fs_initcall(dma_init);
+
 struct dma_map_ops *dma_get_ops(struct device *dev)
 {
 	return dma_ops;

arch/ia64/kernel/ia64_ksyms.c

@@ -21,6 +21,7 @@ EXPORT_SYMBOL(csum_ipv6_magic);
 
 #include <asm/page.h>
 EXPORT_SYMBOL(clear_page);
+EXPORT_SYMBOL(copy_page);
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 #include <linux/bootmem.h>
@@ -60,9 +61,6 @@ EXPORT_SYMBOL(__udivdi3);
 EXPORT_SYMBOL(__moddi3);
 EXPORT_SYMBOL(__umoddi3);
 
-#include <asm/page.h>
-EXPORT_SYMBOL(copy_page);
-
 #if defined(CONFIG_MD_RAID456) || defined(CONFIG_MD_RAID456_MODULE)
 extern void xor_ia64_2(void);
 extern void xor_ia64_3(void);

arch/ia64/kernel/iosapic.c

@@ -1072,6 +1072,10 @@ iosapic_init (unsigned long phys_addr, unsigned int gsi_base)
 	}
 
 	addr = ioremap(phys_addr, 0);
+	if (addr == NULL) {
+		spin_unlock_irqrestore(&iosapic_lock, flags);
+		return -ENOMEM;
+	}
 	ver = iosapic_version(addr);
 	if ((err = iosapic_check_gsi_range(gsi_base, ver))) {
 		iounmap(addr);

arch/ia64/kernel/pci-dma.c

@@ -69,11 +69,6 @@ iommu_dma_init(void)
 
 int iommu_dma_supported(struct device *dev, u64 mask)
 {
-	struct dma_map_ops *ops = platform_dma_get_ops(dev);
-
-	if (ops->dma_supported)
-		return ops->dma_supported(dev, mask);
-
 	/* Copied from i386. Doesn't make much sense, because it will
 	   only work for pci_alloc_coherent.
 	   The caller just has to use GFP_DMA in this case. */

arch/ia64/kernel/ptrace.c

@@ -15,7 +15,6 @@
 #include <linux/mm.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
-#include <linux/smp_lock.h>
 #include <linux/user.h>
 #include <linux/security.h>
 #include <linux/audit.h>

arch/ia64/kernel/topology.c

@@ -372,6 +372,10 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 	retval = kobject_init_and_add(&all_cpu_cache_info[cpu].kobj,
 				      &cache_ktype_percpu_entry, &sys_dev->kobj,
 				      "%s", "cache");
+	if (unlikely(retval < 0)) {
+		cpu_cache_sysfs_exit(cpu);
+		return retval;
+	}
 
 	for (i = 0; i < all_cpu_cache_info[cpu].num_cache_leaves; i++) {
 		this_object = LEAF_KOBJECT_PTR(cpu,i);
@@ -385,7 +389,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 			}
 			kobject_put(&all_cpu_cache_info[cpu].kobj);
 			cpu_cache_sysfs_exit(cpu);
-			break;
+			return retval;
 		}
 		kobject_uevent(&(this_object->kobj), KOBJ_ADD);
 	}

arch/ia64/kvm/mmio.c

@@ -247,7 +247,8 @@ void emulate_io_inst(struct kvm_vcpu *vcpu, u64 padr, u64 ma)
 		vcpu_get_fpreg(vcpu, inst.M9.f2, &v);
 		/* Write high word. FIXME: this is a kludge!  */
 		v.u.bits[1] &= 0x3ffff;
-		mmio_access(vcpu, padr + 8, &v.u.bits[1], 8, ma, IOREQ_WRITE);
+		mmio_access(vcpu, padr + 8, (u64 *)&v.u.bits[1], 8,
+			    ma, IOREQ_WRITE);
 		data = v.u.bits[0];
 		size = 3;
 	} else if (inst.M10.major == 7 && inst.M10.x6 == 0x3B) {
@@ -265,7 +266,8 @@ void emulate_io_inst(struct kvm_vcpu *vcpu, u64 padr, u64 ma)
 
 		/* Write high word.FIXME: this is a kludge!  */
 		v.u.bits[1] &= 0x3ffff;
-		mmio_access(vcpu, padr + 8, &v.u.bits[1], 8, ma, IOREQ_WRITE);
+		mmio_access(vcpu, padr + 8, (u64 *)&v.u.bits[1],
+			    8, ma, IOREQ_WRITE);
 		data = v.u.bits[0];
 		size = 3;
 	} else if (inst.M10.major == 7 && inst.M10.x6 == 0x31) {

arch/ia64/kvm/vcpu.c

@@ -461,7 +461,7 @@ void setreg(unsigned long regnum, unsigned long val,
 u64 vcpu_get_gr(struct kvm_vcpu *vcpu, unsigned long reg)
 {
 	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
-	u64 val;
+	unsigned long val;
 
 	if (!reg)
 		return 0;
@@ -469,7 +469,7 @@ u64 vcpu_get_gr(struct kvm_vcpu *vcpu, unsigned long reg)
 	return val;
 }
 
-void vcpu_set_gr(struct kvm_vcpu *vcpu, u64 reg, u64 value, int nat)
+void vcpu_set_gr(struct kvm_vcpu *vcpu, unsigned long reg, u64 value, int nat)
 {
 	struct kvm_pt_regs *regs = vcpu_regs(vcpu);
 	long sof = (regs->cr_ifs) & 0x7f;
@@ -1072,7 +1072,7 @@ void kvm_ttag(struct kvm_vcpu *vcpu, INST64 inst)
 	vcpu_set_gr(vcpu, inst.M46.r1, tag, 0);
 }
 
-int vcpu_tpa(struct kvm_vcpu *vcpu, u64 vadr, u64 *padr)
+int vcpu_tpa(struct kvm_vcpu *vcpu, u64 vadr, unsigned long *padr)
 {
 	struct thash_data *data;
 	union ia64_isr visr, pt_isr;

arch/ia64/kvm/vcpu.h

@@ -686,14 +686,15 @@ static inline int highest_inservice_irq(struct kvm_vcpu *vcpu)
 	return highest_bits((int *)&(VMX(vcpu, insvc[0])));
 }
 
-extern void vcpu_get_fpreg(struct kvm_vcpu *vcpu, u64 reg,
+extern void vcpu_get_fpreg(struct kvm_vcpu *vcpu, unsigned long reg,
 					struct ia64_fpreg *val);
-extern void vcpu_set_fpreg(struct kvm_vcpu *vcpu, u64 reg,
+extern void vcpu_set_fpreg(struct kvm_vcpu *vcpu, unsigned long reg,
 					struct ia64_fpreg *val);
-extern u64 vcpu_get_gr(struct kvm_vcpu *vcpu, u64 reg);
-extern void vcpu_set_gr(struct kvm_vcpu *vcpu, u64 reg, u64 val, int nat);
-extern u64 vcpu_get_psr(struct kvm_vcpu *vcpu);
-extern void vcpu_set_psr(struct kvm_vcpu *vcpu, u64 val);
+extern u64 vcpu_get_gr(struct kvm_vcpu *vcpu, unsigned long reg);
+extern void vcpu_set_gr(struct kvm_vcpu *vcpu, unsigned long reg,
+			u64 val, int nat);
+extern unsigned long vcpu_get_psr(struct kvm_vcpu *vcpu);
+extern void vcpu_set_psr(struct kvm_vcpu *vcpu, unsigned long val);
 extern u64 vcpu_thash(struct kvm_vcpu *vcpu, u64 vadr);
 extern void vcpu_bsw0(struct kvm_vcpu *vcpu);
 extern void thash_vhpt_insert(struct kvm_vcpu *v, u64 pte,

arch/ia64/pci/pci.c

@@ -537,7 +537,7 @@ pcibios_align_resource (void *data, struct resource *res,
 /*
  * PCI BIOS setup, always defaults to SAL interface
  */
-char * __devinit
+char * __init
 pcibios_setup (char *str)
 {
 	return str;