56 files changed, 263 insertions, 139 deletions
diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index 58a7e46affda..e7cbaa02cd0b 100644
--- a/arch/ia64/Makefile
+++ b/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@@ -41,11 +41,6 @@ $(error Sorry, you need a newer version of the assember, one that is built from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
diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h
index e2ca80037335..57a2787bc9fb 100644
--- a/arch/ia64/include/asm/bitops.h
+++ b/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;
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 0a9cc73d35c7..8840a690d1e7 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/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
diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c
index 2d311864e359..8ebccb589e1c 100644
--- a/arch/ia64/kernel/ia64_ksyms.c
+++ b/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);
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index c48b03f2b61d..dab4d393908c 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/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);
diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c
index 05695962fe44..f6b1ff0aea76 100644
--- a/arch/ia64/kernel/pci-dma.c
+++ b/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. */
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index bc80dff1df7a..8f060352e129 100644
--- a/arch/ia64/kernel/topology.c
+++ b/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);
        }
diff --git a/arch/ia64/kvm/mmio.c b/arch/ia64/kvm/mmio.c
index 21f63fffc379..9bf55afd08d0 100644
--- a/arch/ia64/kvm/mmio.c
+++ b/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) {
diff --git a/arch/ia64/kvm/vcpu.c b/arch/ia64/kvm/vcpu.c
index 46b02cbcc874..cc406d064a09 100644
--- a/arch/ia64/kvm/vcpu.c
+++ b/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;
diff --git a/arch/ia64/kvm/vcpu.h b/arch/ia64/kvm/vcpu.h
index 042af92ced83..360724d3ae69 100644
--- a/arch/ia64/kvm/vcpu.h
+++ b/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 u64 vcpu_get_gr(struct kvm_vcpu *vcpu, unsigned long reg);
-extern void vcpu_set_gr(struct kvm_vcpu *vcpu, u64 reg, u64 val, int nat);
+extern void vcpu_set_gr(struct kvm_vcpu *vcpu, unsigned long reg,
-extern u64 vcpu_get_psr(struct kvm_vcpu *vcpu);
+                        u64 val, int nat);
-extern void vcpu_set_psr(struct kvm_vcpu *vcpu, u64 val);
+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,
diff --git a/arch/mn10300/include/asm/pci.h b/arch/mn10300/include/asm/pci.h
index 35d2ed6396f6..19aecc90f7a4 100644
--- a/arch/mn10300/include/asm/pci.h
+++ b/arch/mn10300/include/asm/pci.h
@@ -59,7 +59,6 @@ void pcibios_penalize_isa_irq(int irq);
 #include <linux/slab.h>
 #include <asm/scatterlist.h>
 #include <linux/string.h>
-#include <linux/mm.h>
 #include <asm/io.h>
 struct pci_dev;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index dfdf13c9fefd..fddc3ed715fa 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -34,7 +34,7 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 /* We don't currently support large pages. */
-#define KVM_PAGES_PER_HPAGE (1<<31)
+#define KVM_PAGES_PER_HPAGE (1UL << 31)
 struct kvm;
 struct kvm_run;
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 20a60d661ba8..ccf129d47d84 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -7,6 +7,7 @@
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/lmb.h>
 #include <asm/bug.h>
 #include <asm/abs_addr.h>
@@ -90,11 +91,10 @@ static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg,
 static int dma_direct_dma_supported(struct device *dev, u64 mask)
 {
 #ifdef CONFIG_PPC64
-        /* Could be improved to check for memory though it better be
+        /* Could be improved so platforms can set the limit in case
-         * done via some global so platforms can set the limit in case
         * they have limited DMA windows
         */
-        return mask >= DMA_BIT_MASK(32);
+        return mask >= (lmb_end_of_DRAM() - 1);
 #else
        return 1;
 #endif
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index f04f5301b1b4..4d613415c435 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -386,7 +386,7 @@ no_timer:
        }
        __unset_cpu_idle(vcpu);
        __set_current_state(TASK_RUNNING);
-        remove_wait_queue(&vcpu->wq, &wait);
+        remove_wait_queue(&vcpu->arch.local_int.wq, &wait);
        spin_unlock_bh(&vcpu->arch.local_int.lock);
        spin_unlock(&vcpu->arch.local_int.float_int->lock);
        hrtimer_try_to_cancel(&vcpu->arch.ckc_timer);
diff --git a/arch/sh/boards/board-ap325rxa.c b/arch/sh/boards/board-ap325rxa.c
index 7ffd1b4315bd..b9c88cc519e2 100644
--- a/arch/sh/boards/board-ap325rxa.c
+++ b/arch/sh/boards/board-ap325rxa.c
@@ -547,7 +547,7 @@ static int __init ap325rxa_devices_setup(void)
        return platform_add_devices(ap325rxa_devices,
                                ARRAY_SIZE(ap325rxa_devices));
 }
-device_initcall(ap325rxa_devices_setup);
+arch_initcall(ap325rxa_devices_setup);
 /* Return the board specific boot mode pin configuration */
 static int ap325rxa_mode_pins(void)
diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index f70f4644deb4..f9b2e4df35b9 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -608,7 +608,7 @@ static int __init migor_devices_setup(void)
        return platform_add_devices(migor_devices, ARRAY_SIZE(migor_devices));
 }
-__initcall(migor_devices_setup);
+arch_initcall(migor_devices_setup);
 /* Return the board specific boot mode pin configuration */
 static int migor_mode_pins(void)
diff --git a/arch/sh/kernel/cpu/sh2/setup-sh7619.c b/arch/sh/kernel/cpu/sh2/setup-sh7619.c
index 13798733f2db..8555c05e8667 100644
--- a/arch/sh/kernel/cpu/sh2/setup-sh7619.c
+++ b/arch/sh/kernel/cpu/sh2/setup-sh7619.c
@@ -187,7 +187,7 @@ static int __init sh7619_devices_setup(void)
        return platform_add_devices(sh7619_devices,
                                    ARRAY_SIZE(sh7619_devices));
 }
-__initcall(sh7619_devices_setup);
+arch_initcall(sh7619_devices_setup);
 void __init plat_irq_setup(void)
 {
diff --git a/arch/sh/kernel/cpu/sh2a/setup-mxg.c b/arch/sh/kernel/cpu/sh2a/setup-mxg.c
index 869c2da4820b..b67376445315 100644
--- a/arch/sh/kernel/cpu/sh2a/setup-mxg.c
+++ b/arch/sh/kernel/cpu/sh2a/setup-mxg.c
@@ -238,7 +238,7 @@ static int __init mxg_devices_setup(void)
        return platform_add_devices(mxg_devices,
                                    ARRAY_SIZE(mxg_devices));
 }
-__initcall(mxg_devices_setup);
+arch_initcall(mxg_devices_setup);
 void __init plat_irq_setup(void)
 {
diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7201.c b/arch/sh/kernel/cpu/sh2a/setup-sh7201.c
index d8febe128066..fbde5b75deb9 100644
--- a/arch/sh/kernel/cpu/sh2a/setup-sh7201.c
+++ b/arch/sh/kernel/cpu/sh2a/setup-sh7201.c
@@ -357,7 +357,7 @@ static int __init sh7201_devices_setup(void)
        return platform_add_devices(sh7201_devices,
                                    ARRAY_SIZE(sh7201_devices));
 }
-__initcall(sh7201_devices_setup);
+arch_initcall(sh7201_devices_setup);
 void __init plat_irq_setup(void)
 {
diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7203.c b/arch/sh/kernel/cpu/sh2a/setup-sh7203.c
index 62e3039d2398..d3fd536c9a84 100644
--- a/arch/sh/kernel/cpu/sh2a/setup-sh7203.c
+++ b/arch/sh/kernel/cpu/sh2a/setup-sh7203.c
@@ -367,7 +367,7 @@ static int __init sh7203_devices_setup(void)
        return platform_add_devices(sh7203_devices,
                                    ARRAY_SIZE(sh7203_devices));
 }
-__initcall(sh7203_devices_setup);
+arch_initcall(sh7203_devices_setup);
 void __init plat_irq_setup(void)
 {
diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7206.c b/arch/sh/kernel/cpu/sh2a/setup-sh7206.c
index 3e6f3d7a58be..a9ccc5e8d9e9 100644
--- a/arch/sh/kernel/cpu/sh2a/setup-sh7206.c
+++ b/arch/sh/kernel/cpu/sh2a/setup-sh7206.c
@@ -338,7 +338,7 @@ static int __init sh7206_devices_setup(void)
        return platform_add_devices(sh7206_devices,
                                    ARRAY_SIZE(sh7206_devices));
 }
-__initcall(sh7206_devices_setup);
+arch_initcall(sh7206_devices_setup);
 void __init plat_irq_setup(void)
 {
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7705.c b/arch/sh/kernel/cpu/sh3/setup-sh7705.c
index 88f742fed9ed..c23105983878 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh7705.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh7705.c
@@ -222,7 +222,7 @@ static int __init sh7705_devices_setup(void)
        return platform_add_devices(sh7705_devices,
                                    ARRAY_SIZE(sh7705_devices));
 }
-__initcall(sh7705_devices_setup);
+arch_initcall(sh7705_devices_setup);
 static struct platform_device *sh7705_early_devices[] __initdata = {
        &tmu0_device,
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
index c56306798584..347ab35d0697 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
@@ -250,7 +250,7 @@ static int __init sh770x_devices_setup(void)
        return platform_add_devices(sh770x_devices,
                ARRAY_SIZE(sh770x_devices));
 }
-__initcall(sh770x_devices_setup);
+arch_initcall(sh770x_devices_setup);
 static struct platform_device *sh770x_early_devices[] __initdata = {
        &tmu0_device,
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7710.c b/arch/sh/kernel/cpu/sh3/setup-sh7710.c
index efa76c8148f4..717e90ae1097 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh7710.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh7710.c
@@ -226,7 +226,7 @@ static int __init sh7710_devices_setup(void)
        return platform_add_devices(sh7710_devices,
                                    ARRAY_SIZE(sh7710_devices));
 }
-__initcall(sh7710_devices_setup);
+arch_initcall(sh7710_devices_setup);
 static struct platform_device *sh7710_early_devices[] __initdata = {
        &tmu0_device,
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7720.c b/arch/sh/kernel/cpu/sh3/setup-sh7720.c
index 5b2107798edb..74d8baaf8e96 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh7720.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh7720.c
@@ -388,7 +388,7 @@ static int __init sh7720_devices_setup(void)
        return platform_add_devices(sh7720_devices,
                                    ARRAY_SIZE(sh7720_devices));
 }
-__initcall(sh7720_devices_setup);
+arch_initcall(sh7720_devices_setup);
 static struct platform_device *sh7720_early_devices[] __initdata = {
        &cmt0_device,
diff --git a/arch/sh/kernel/cpu/sh4/setup-sh4-202.c b/arch/sh/kernel/cpu/sh4/setup-sh4-202.c
index 6d088d123591..de4827df19aa 100644
--- a/arch/sh/kernel/cpu/sh4/setup-sh4-202.c
+++ b/arch/sh/kernel/cpu/sh4/setup-sh4-202.c
@@ -138,7 +138,7 @@ static int __init sh4202_devices_setup(void)
        return platform_add_devices(sh4202_devices,
                                    ARRAY_SIZE(sh4202_devices));
 }
-__initcall(sh4202_devices_setup);
+arch_initcall(sh4202_devices_setup);
 static struct platform_device *sh4202_early_devices[] __initdata = {
        &tmu0_device,
diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7750.c b/arch/sh/kernel/cpu/sh4/setup-sh7750.c
index 851672d15cf4..1b8b122e8f3d 100644
--- a/arch/sh/kernel/cpu/sh4/setup-sh7750.c
+++ b/arch/sh/kernel/cpu/sh4/setup-sh7750.c
@@ -239,7 +239,7 @@ static int __init sh7750_devices_setup(void)
        return platform_add_devices(sh7750_devices,
                                    ARRAY_SIZE(sh7750_devices));
 }
-__initcall(sh7750_devices_setup);
+arch_initcall(sh7750_devices_setup);
 static struct platform_device *sh7750_early_devices[] __initdata = {
        &tmu0_device,
diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7760.c b/arch/sh/kernel/cpu/sh4/setup-sh7760.c
index 5b822519bd90..7fbb7be9284c 100644
--- a/arch/sh/kernel/cpu/sh4/setup-sh7760.c
+++ b/arch/sh/kernel/cpu/sh4/setup-sh7760.c
@@ -265,7 +265,7 @@ static int __init sh7760_devices_setup(void)
        return platform_add_devices(sh7760_devices,
                                    ARRAY_SIZE(sh7760_devices));
 }
-__initcall(sh7760_devices_setup);
+arch_initcall(sh7760_devices_setup);
 static struct platform_device *sh7760_early_devices[] __initdata = {
        &tmu0_device,
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7343.c b/arch/sh/kernel/cpu/sh4a/setup-sh7343.c
index 6307e087c864..ac4d5672ec1a 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7343.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7343.c
@@ -325,7 +325,7 @@ static int __init sh7343_devices_setup(void)
        return platform_add_devices(sh7343_devices,
                                    ARRAY_SIZE(sh7343_devices));
 }
-__initcall(sh7343_devices_setup);
+arch_initcall(sh7343_devices_setup);
 static struct platform_device *sh7343_early_devices[] __initdata = {
        &cmt_device,
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c
index c18f7d09281b..1a956b1beccc 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c
@@ -318,7 +318,7 @@ static int __init sh7366_devices_setup(void)
        return platform_add_devices(sh7366_devices,
                                    ARRAY_SIZE(sh7366_devices));
 }
-__initcall(sh7366_devices_setup);
+arch_initcall(sh7366_devices_setup);
 static struct platform_device *sh7366_early_devices[] __initdata = {
        &cmt_device,
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c
index ea524a2da3e4..cda76ebf87c3 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c
@@ -359,7 +359,7 @@ static int __init sh7722_devices_setup(void)
        return platform_add_devices(sh7722_devices,
                                    ARRAY_SIZE(sh7722_devices));
 }
-__initcall(sh7722_devices_setup);
+arch_initcall(sh7722_devices_setup);
 static struct platform_device *sh7722_early_devices[] __initdata = {
        &cmt_device,
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c
index e1bb80b2a27b..b45dace9539f 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c
@@ -473,7 +473,7 @@ static int __init sh7723_devices_setup(void)
        return platform_add_devices(sh7723_devices,
                                    ARRAY_SIZE(sh7723_devices));
 }
-__initcall(sh7723_devices_setup);
+arch_initcall(sh7723_devices_setup);
 static struct platform_device *sh7723_early_devices[] __initdata = {
        &cmt_device,
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c
index e5ac9eb11c63..a04edaab9a29 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c
@@ -508,7 +508,7 @@ static int __init sh7724_devices_setup(void)
        return platform_add_devices(sh7724_devices,
                                    ARRAY_SIZE(sh7724_devices));
 }
-device_initcall(sh7724_devices_setup);
+arch_initcall(sh7724_devices_setup);
 static struct platform_device *sh7724_early_devices[] __initdata = {
        &cmt_device,
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7763.c b/arch/sh/kernel/cpu/sh4a/setup-sh7763.c
index f1e0c0d36da7..4659fff6b842 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7763.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7763.c
@@ -314,7 +314,7 @@ static int __init sh7763_devices_setup(void)
        return platform_add_devices(sh7763_devices,
                                    ARRAY_SIZE(sh7763_devices));
 }
-__initcall(sh7763_devices_setup);
+arch_initcall(sh7763_devices_setup);
 static struct platform_device *sh7763_early_devices[] __initdata = {
        &tmu0_device,
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7770.c b/arch/sh/kernel/cpu/sh4a/setup-sh7770.c
index 1e86209db284..eead08d89d32 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7770.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7770.c
@@ -368,7 +368,7 @@ static int __init sh7770_devices_setup(void)
        return platform_add_devices(sh7770_devices,
                                    ARRAY_SIZE(sh7770_devices));
 }
-__initcall(sh7770_devices_setup);
+arch_initcall(sh7770_devices_setup);
 static struct platform_device *sh7770_early_devices[] __initdata = {
        &tmu0_device,
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c
index 715e05b431e5..2c901f446959 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c
@@ -256,7 +256,7 @@ static int __init sh7780_devices_setup(void)
        return platform_add_devices(sh7780_devices,
                                    ARRAY_SIZE(sh7780_devices));
 }
-__initcall(sh7780_devices_setup);
+arch_initcall(sh7780_devices_setup);
 static struct platform_device *sh7780_early_devices[] __initdata = {
        &tmu0_device,
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c
index af561402570b..7f6c718b6c36 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c
@@ -263,7 +263,7 @@ static int __init sh7785_devices_setup(void)
        return platform_add_devices(sh7785_devices,
                                    ARRAY_SIZE(sh7785_devices));
 }
-__initcall(sh7785_devices_setup);
+arch_initcall(sh7785_devices_setup);
 static struct platform_device *sh7785_early_devices[] __initdata = {
        &tmu0_device,
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c
index b70049470a0b..0104a8ec5369 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c
@@ -547,7 +547,7 @@ static int __init sh7786_devices_setup(void)
        return platform_add_devices(sh7786_devices,
                                    ARRAY_SIZE(sh7786_devices));
 }
-device_initcall(sh7786_devices_setup);
+arch_initcall(sh7786_devices_setup);
 void __init plat_early_device_setup(void)
 {
diff --git a/arch/sh/kernel/cpu/sh4a/setup-shx3.c b/arch/sh/kernel/cpu/sh4a/setup-shx3.c
index 53c65fd9ccef..07f078961c71 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-shx3.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-shx3.c
@@ -256,7 +256,7 @@ static int __init shx3_devices_setup(void)
        return platform_add_devices(shx3_devices,
                                    ARRAY_SIZE(shx3_devices));
 }
-__initcall(shx3_devices_setup);
+arch_initcall(shx3_devices_setup);
 void __init plat_early_device_setup(void)
 {
diff --git a/arch/sh/kernel/cpu/sh5/setup-sh5.c b/arch/sh/kernel/cpu/sh5/setup-sh5.c
index f5ff1ac57fc2..6a0f82f70032 100644
--- a/arch/sh/kernel/cpu/sh5/setup-sh5.c
+++ b/arch/sh/kernel/cpu/sh5/setup-sh5.c
@@ -186,7 +186,7 @@ static int __init sh5_devices_setup(void)
        return platform_add_devices(sh5_devices,
                                    ARRAY_SIZE(sh5_devices));
 }
-__initcall(sh5_devices_setup);
+arch_initcall(sh5_devices_setup);
 void __init plat_early_device_setup(void)
 {
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 738bdc6b0f8b..13ffa5df37d7 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -24,6 +24,7 @@ config X86
        select HAVE_UNSTABLE_SCHED_CLOCK
        select HAVE_IDE
        select HAVE_OPROFILE
+        select HAVE_PERF_COUNTERS if (!M386 && !M486)
        select HAVE_IOREMAP_PROT
        select HAVE_KPROBES
        select ARCH_WANT_OPTIONAL_GPIOLIB
@@ -742,7 +743,6 @@ config X86_UP_IOAPIC
 config X86_LOCAL_APIC
        def_bool y
        depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC
-        select HAVE_PERF_COUNTERS if (!M386 && !M486)
 config X86_IO_APIC
        def_bool y
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 2ed4e2bb3b32..a5371ec36776 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -17,11 +17,13 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
        return x2apic_enabled();
 }
-/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
+/*
+ * need to use more than cpu 0, because we need more vectors when
+ * MSI-X are used.
+ */
 static const struct cpumask *x2apic_target_cpus(void)
 {
-        return cpumask_of(0);
+        return cpu_online_mask;
 }
 /*
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 0b631c6a2e00..a8989aadc99a 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -27,11 +27,13 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
                return 0;
 }
-/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
+/*
+ * need to use more than cpu 0, because we need more vectors when
+ * MSI-X are used.
+ */
 static const struct cpumask *x2apic_target_cpus(void)
 {
-        return cpumask_of(0);
+        return cpu_online_mask;
 }
 static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e2485b03f1cf..63fddcd082cd 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -400,6 +400,13 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
                level = cpuid_eax(1);
                if((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
                        set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+                /*
+                 * Some BIOSes incorrectly force this feature, but only K8
+                 * revision D (model = 0x14) and later actually support it.
+                 */
+                if (c->x86_model < 0x14)
+                        clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
        }
        if (c->x86 == 0x10 || c->x86 == 0x11)
                set_cpu_cap(c, X86_FEATURE_REP_GOOD);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f1961c07af9a..5ce60a88027b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -59,7 +59,30 @@ void __init setup_cpu_local_masks(void)
        alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
 }
-static const struct cpu_dev *this_cpu __cpuinitdata;
+static void __cpuinit default_init(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
+        display_cacheinfo(c);
+#else
+        /* Not much we can do here... */
+        /* Check if at least it has cpuid */
+        if (c->cpuid_level == -1) {
+                /* No cpuid. It must be an ancient CPU */
+                if (c->x86 == 4)
+                        strcpy(c->x86_model_id, "486");
+                else if (c->x86 == 3)
+                        strcpy(c->x86_model_id, "386");
+        }
+#endif
+}
+static const struct cpu_dev __cpuinitconst default_cpu = {
+        .c_init         = default_init,
+        .c_vendor       = "Unknown",
+        .c_x86_vendor   = X86_VENDOR_UNKNOWN,
+};
+static const struct cpu_dev *this_cpu __cpuinitdata = &default_cpu;
 DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 #ifdef CONFIG_X86_64
@@ -332,29 +355,6 @@ void switch_to_new_gdt(int cpu)
 static const struct cpu_dev *__cpuinitdata cpu_devs[X86_VENDOR_NUM] = {};
-static void __cpuinit default_init(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_X86_64
-        display_cacheinfo(c);
-#else
-        /* Not much we can do here... */
-        /* Check if at least it has cpuid */
-        if (c->cpuid_level == -1) {
-                /* No cpuid. It must be an ancient CPU */
-                if (c->x86 == 4)
-                        strcpy(c->x86_model_id, "486");
-                else if (c->x86 == 3)
-                        strcpy(c->x86_model_id, "386");
-        }
-#endif
-}
-static const struct cpu_dev __cpuinitconst default_cpu = {
-        .c_init = default_init,
-        .c_vendor = "Unknown",
-        .c_x86_vendor = X86_VENDOR_UNKNOWN,
-};
 static void __cpuinit get_model_name(struct cpuinfo_x86 *c)
 {
        unsigned int *v;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index bff8dd191dd5..8bc64cfbe936 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -36,6 +36,7 @@
 static DEFINE_PER_CPU(__u64, next_check) = INITIAL_JIFFIES;
 static DEFINE_PER_CPU(unsigned long, thermal_throttle_count);
+static DEFINE_PER_CPU(bool, thermal_throttle_active);
 static atomic_t therm_throt_en          = ATOMIC_INIT(0);
@@ -96,24 +97,27 @@ static int therm_throt_process(int curr)
 {
        unsigned int cpu = smp_processor_id();
        __u64 tmp_jiffs = get_jiffies_64();
+        bool was_throttled = __get_cpu_var(thermal_throttle_active);
+        bool is_throttled = __get_cpu_var(thermal_throttle_active) = curr;
-        if (curr)
+        if (is_throttled)
                __get_cpu_var(thermal_throttle_count)++;
-        if (time_before64(tmp_jiffs, __get_cpu_var(next_check)))
+        if (!(was_throttled ^ is_throttled) &&
+            time_before64(tmp_jiffs, __get_cpu_var(next_check)))
                return 0;
        __get_cpu_var(next_check) = tmp_jiffs + CHECK_INTERVAL;
        /* if we just entered the thermal event */
-        if (curr) {
+        if (is_throttled) {
                printk(KERN_CRIT "CPU%d: Temperature above threshold, "
-                       "cpu clock throttled (total events = %lu)\n", cpu,
+                       "cpu clock throttled (total events = %lu)\n",
-                       __get_cpu_var(thermal_throttle_count));
+                       cpu, __get_cpu_var(thermal_throttle_count));
                add_taint(TAINT_MACHINE_CHECK);
-        } else {
+        } else if (was_throttled) {
-                printk(KERN_CRIT "CPU%d: Temperature/speed normal\n", cpu);
+                printk(KERN_INFO "CPU%d: Temperature/speed normal\n", cpu);
        }
        return 1;
diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index b237c181aa41..396e35db7058 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -97,6 +97,7 @@ struct x86_pmu {
        int             num_counters_fixed;
        int             counter_bits;
        u64             counter_mask;
+        int             apic;
        u64             max_period;
        u64             intel_ctrl;
        void            (*enable_bts)(u64 config);
@@ -116,8 +117,8 @@ static const u64 p6_perfmon_event_map[] =
 {
  [PERF_COUNT_HW_CPU_CYCLES]            = 0x0079,
  [PERF_COUNT_HW_INSTRUCTIONS]          = 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]      = 0x0000,
+  [PERF_COUNT_HW_CACHE_REFERENCES]      = 0x0f2e,
-  [PERF_COUNT_HW_CACHE_MISSES]          = 0x0000,
+  [PERF_COUNT_HW_CACHE_MISSES]          = 0x012e,
  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]   = 0x00c4,
  [PERF_COUNT_HW_BRANCH_MISSES]         = 0x00c5,
  [PERF_COUNT_HW_BUS_CYCLES]            = 0x0062,
@@ -660,6 +661,7 @@ static DEFINE_MUTEX(pmc_reserve_mutex);
 static bool reserve_pmc_hardware(void)
 {
+#ifdef CONFIG_X86_LOCAL_APIC
        int i;
        if (nmi_watchdog == NMI_LOCAL_APIC)
@@ -674,9 +676,11 @@ static bool reserve_pmc_hardware(void)
                if (!reserve_evntsel_nmi(x86_pmu.eventsel + i))
                        goto eventsel_fail;
        }
+#endif
        return true;
+#ifdef CONFIG_X86_LOCAL_APIC
 eventsel_fail:
        for (i--; i >= 0; i--)
                release_evntsel_nmi(x86_pmu.eventsel + i);
@@ -691,10 +695,12 @@ perfctr_fail:
                enable_lapic_nmi_watchdog();
        return false;
+#endif
 }
 static void release_pmc_hardware(void)
 {
+#ifdef CONFIG_X86_LOCAL_APIC
        int i;
        for (i = 0; i < x86_pmu.num_counters; i++) {
@@ -704,6 +710,7 @@ static void release_pmc_hardware(void)
        if (nmi_watchdog == NMI_LOCAL_APIC)
                enable_lapic_nmi_watchdog();
+#endif
 }
 static inline bool bts_available(void)
@@ -934,6 +941,15 @@ static int __hw_perf_counter_init(struct perf_counter *counter)
                hwc->sample_period = x86_pmu.max_period;
                hwc->last_period = hwc->sample_period;
                atomic64_set(&hwc->period_left, hwc->sample_period);
+        } else {
+                /*
+                 * If we have a PMU initialized but no APIC
+                 * interrupts, we cannot sample hardware
+                 * counters (user-space has to fall back and
+                 * sample via a hrtimer based software counter):
+                 */
+                if (!x86_pmu.apic)
+                        return -EOPNOTSUPP;
        }
        counter->destroy = hw_perf_counter_destroy;
@@ -1755,18 +1771,22 @@ void smp_perf_pending_interrupt(struct pt_regs *regs)
 void set_perf_counter_pending(void)
 {
+#ifdef CONFIG_X86_LOCAL_APIC
        apic->send_IPI_self(LOCAL_PENDING_VECTOR);
+#endif
 }
 void perf_counters_lapic_init(void)
 {
-        if (!x86_pmu_initialized())
+#ifdef CONFIG_X86_LOCAL_APIC
+        if (!x86_pmu.apic || !x86_pmu_initialized())
                return;
        /*
         * Always use NMI for PMU
         */
        apic_write(APIC_LVTPC, APIC_DM_NMI);
+#endif
 }
 static int __kprobes
@@ -1790,7 +1810,9 @@ perf_counter_nmi_handler(struct notifier_block *self,
        regs = args->regs;
+#ifdef CONFIG_X86_LOCAL_APIC
        apic_write(APIC_LVTPC, APIC_DM_NMI);
+#endif
        /*
         * Can't rely on the handled return value to say it was our NMI, two
         * counters could trigger 'simultaneously' raising two back-to-back NMIs.
@@ -1821,6 +1843,7 @@ static struct x86_pmu p6_pmu = {
        .event_map              = p6_pmu_event_map,
        .raw_event              = p6_pmu_raw_event,
        .max_events             = ARRAY_SIZE(p6_perfmon_event_map),
+        .apic                   = 1,
        .max_period             = (1ULL << 31) - 1,
        .version                = 0,
        .num_counters           = 2,
@@ -1847,6 +1870,7 @@ static struct x86_pmu intel_pmu = {
        .event_map              = intel_pmu_event_map,
        .raw_event              = intel_pmu_raw_event,
        .max_events             = ARRAY_SIZE(intel_perfmon_event_map),
+        .apic                   = 1,
        /*
         * Intel PMCs cannot be accessed sanely above 32 bit width,
         * so we install an artificial 1<<31 period regardless of
@@ -1872,6 +1896,7 @@ static struct x86_pmu amd_pmu = {
        .num_counters           = 4,
        .counter_bits           = 48,
        .counter_mask           = (1ULL << 48) - 1,
+        .apic                   = 1,
        /* use highest bit to detect overflow */
        .max_period             = (1ULL << 47) - 1,
 };
@@ -1897,13 +1922,14 @@ static int p6_pmu_init(void)
                return -ENODEV;
        }
+        x86_pmu = p6_pmu;
        if (!cpu_has_apic) {
-                pr_info("no Local APIC, try rebooting with lapic");
+                pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n");
-                return -ENODEV;
+                pr_info("no hardware sampling interrupt available.\n");
+                x86_pmu.apic = 0;
        }
-        x86_pmu                         = p6_pmu;
        return 0;
 }
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index 19ccf6d0dccf..fe26ba3e3451 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -354,7 +354,7 @@ void __init efi_init(void)
         */
        c16 = tmp = early_ioremap(efi.systab->fw_vendor, 2);
        if (c16) {
-                for (i = 0; i < sizeof(vendor) && *c16; ++i)
+                for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i)
                        vendor[i] = *c16++;
                vendor[i] = '\0';
        } else
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 834c9da8bf9d..a06e8d101844 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -405,7 +405,7 @@ EXPORT_SYMBOL(machine_real_restart);
 #endif /* CONFIG_X86_32 */
 /*
- * Apple MacBook5,2 (2009 MacBook) needs reboot=p
+ * Some Apple MacBook and MacBookPro's needs reboot=p to be able to reboot
 */
 static int __init set_pci_reboot(const struct dmi_system_id *d)
 {
@@ -418,12 +418,20 @@ static int __init set_pci_reboot(const struct dmi_system_id *d)
 }
 static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
-        {       /* Handle problems with rebooting on Apple MacBook5,2 */
+        {       /* Handle problems with rebooting on Apple MacBook5 */
                .callback = set_pci_reboot,
-                .ident = "Apple MacBook",
+                .ident = "Apple MacBook5",
                .matches = {
                        DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
-                        DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5,2"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"),
+                },
+        },
+        {       /* Handle problems with rebooting on Apple MacBookPro5 */
+                .callback = set_pci_reboot,
+                .ident = "Apple MacBookPro5",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro5"),
                },
        },
        { }
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 6e1a368d21d4..71f4368b357e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -275,15 +275,20 @@ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin)
 * use the TSC value at the transitions to calculate a pretty
 * good value for the TSC frequencty.
 */
+static inline int pit_verify_msb(unsigned char val)
+{
+        /* Ignore LSB */
+        inb(0x42);
+        return inb(0x42) == val;
+}
 static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap)
 {
        int count;
        u64 tsc = 0;
        for (count = 0; count < 50000; count++) {
-                /* Ignore LSB */
+                if (!pit_verify_msb(val))
-                inb(0x42);
-                if (inb(0x42) != val)
                        break;
                tsc = get_cycles();
        }
@@ -336,8 +341,7 @@ static unsigned long quick_pit_calibrate(void)
         * to do that is to just read back the 16-bit counter
         * once from the PIT.
         */
-        inb(0x42);
+        pit_verify_msb(0);
-        inb(0x42);
        if (pit_expect_msb(0xff, &tsc, &d1)) {
                for (i = 1; i <= MAX_QUICK_PIT_ITERATIONS; i++) {
@@ -348,8 +352,19 @@ static unsigned long quick_pit_calibrate(void)
                         * Iterate until the error is less than 500 ppm
                         */
                        delta -= tsc;
-                        if (d1+d2 < delta >> 11)
+                        if (d1+d2 >= delta >> 11)
-                                goto success;
+                                continue;
+                        /*
+                         * Check the PIT one more time to verify that
+                         * all TSC reads were stable wrt the PIT.
+                         *
+                         * This also guarantees serialization of the
+                         * last cycle read ('d2') in pit_expect_msb.
+                         */
+                        if (!pit_verify_msb(0xfe - i))
+                                break;
+                        goto success;
                }
        }
        printk("Fast TSC calibration failed\n");
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index b263423fbe2a..95a7289e4b0c 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -441,7 +441,7 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
        ap.ds = __USER_DS;
        ap.es = __USER_DS;
        ap.fs = __KERNEL_PERCPU;
-        ap.gs = 0;
+        ap.gs = __KERNEL_STACK_CANARY;
        ap.eflags = 0;
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 4d6f0d293ee2..21f68e00524f 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -104,6 +104,9 @@ static s64 __kpit_elapsed(struct kvm *kvm)
        ktime_t remaining;
        struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
+        if (!ps->pit_timer.period)
+                return 0;
        /*
         * The Counter does not stop when it reaches zero. In
         * Modes 0, 1, 4, and 5 the Counter ``wraps around'' to
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 7030b5f911bf..0ef5bb2b4043 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -489,16 +489,20 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage)
 *
 * If rmapp bit zero is one, (then rmap & ~1) points to a struct kvm_rmap_desc
 * containing more mappings.
+ *
+ * Returns the number of rmap entries before the spte was added or zero if
+ * the spte was not added.
+ *
 */
-static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
+static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
 {
        struct kvm_mmu_page *sp;
        struct kvm_rmap_desc *desc;
        unsigned long *rmapp;
-        int i;
+        int i, count = 0;
        if (!is_rmap_pte(*spte))
-                return;
+                return count;
        gfn = unalias_gfn(vcpu->kvm, gfn);
        sp = page_header(__pa(spte));
        sp->gfns[spte - sp->spt] = gfn;
@@ -515,8 +519,10 @@ static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
        } else {
                rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte);
                desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
-                while (desc->shadow_ptes[RMAP_EXT-1] && desc->more)
+                while (desc->shadow_ptes[RMAP_EXT-1] && desc->more) {
                        desc = desc->more;
+                        count += RMAP_EXT;
+                }
                if (desc->shadow_ptes[RMAP_EXT-1]) {
                        desc->more = mmu_alloc_rmap_desc(vcpu);
                        desc = desc->more;
@@ -525,6 +531,7 @@ static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
                        ;
                desc->shadow_ptes[i] = spte;
        }
+        return count;
 }
 static void rmap_desc_remove_entry(unsigned long *rmapp,
@@ -754,6 +761,19 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp)
        return young;
 }
+#define RMAP_RECYCLE_THRESHOLD 1000
+static void rmap_recycle(struct kvm_vcpu *vcpu, gfn_t gfn, int lpage)
+{
+        unsigned long *rmapp;
+        gfn = unalias_gfn(vcpu->kvm, gfn);
+        rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage);
+        kvm_unmap_rmapp(vcpu->kvm, rmapp);
+        kvm_flush_remote_tlbs(vcpu->kvm);
+}
 int kvm_age_hva(struct kvm *kvm, unsigned long hva)
 {
        return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
@@ -1407,24 +1427,25 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 */
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages)
 {
+        int used_pages;
+        used_pages = kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages;
+        used_pages = max(0, used_pages);
        /*
         * If we set the number of mmu pages to be smaller be than the
         * number of actived pages , we must to free some mmu pages before we
         * change the value
         */
-        if ((kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages) >
+        if (used_pages > kvm_nr_mmu_pages) {
-            kvm_nr_mmu_pages) {
+                while (used_pages > kvm_nr_mmu_pages) {
-                int n_used_mmu_pages = kvm->arch.n_alloc_mmu_pages
-                                       - kvm->arch.n_free_mmu_pages;
-                while (n_used_mmu_pages > kvm_nr_mmu_pages) {
                        struct kvm_mmu_page *page;
                        page = container_of(kvm->arch.active_mmu_pages.prev,
                                            struct kvm_mmu_page, link);
                        kvm_mmu_zap_page(kvm, page);
-                        n_used_mmu_pages--;
+                        used_pages--;
                }
                kvm->arch.n_free_mmu_pages = 0;
        }
@@ -1740,6 +1761,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 {
        int was_rmapped = 0;
        int was_writeble = is_writeble_pte(*shadow_pte);
+        int rmap_count;
        pgprintk("%s: spte %llx access %x write_fault %d"
                 " user_fault %d gfn %lx\n",
@@ -1781,9 +1803,11 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
        page_header_update_slot(vcpu->kvm, shadow_pte, gfn);
        if (!was_rmapped) {
-                rmap_add(vcpu, shadow_pte, gfn, largepage);
+                rmap_count = rmap_add(vcpu, shadow_pte, gfn, largepage);
                if (!is_rmap_pte(*shadow_pte))
                        kvm_release_pfn_clean(pfn);
+                if (rmap_count > RMAP_RECYCLE_THRESHOLD)
+                        rmap_recycle(vcpu, gfn, largepage);
        } else {
                if (was_writeble)
                        kvm_release_pfn_dirty(pfn);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 71510e07e69e..b1f658ad2f06 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -711,6 +711,7 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
                svm->vmcb->control.tsc_offset += delta;
                vcpu->cpu = cpu;
                kvm_migrate_timers(vcpu);
+                svm->asid_generation = 0;
        }
        for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
@@ -1031,7 +1032,6 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data)
                svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID;
        }
-        svm->vcpu.cpu = svm_data->cpu;
        svm->asid_generation = svm_data->asid_generation;
        svm->vmcb->control.asid = svm_data->next_asid++;
 }
@@ -2300,8 +2300,8 @@ static void pre_svm_run(struct vcpu_svm *svm)
        struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu);
        svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
-        if (svm->vcpu.cpu != cpu ||
+        /* FIXME: handle wraparound of asid_generation */
-            svm->asid_generation != svm_data->asid_generation)
+        if (svm->asid_generation != svm_data->asid_generation)
                new_asid(svm, svm_data);
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 356a0ce85c68..29f912927a58 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3157,8 +3157,8 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
        struct vcpu_vmx *vmx = to_vmx(vcpu);
        enum emulation_result err = EMULATE_DONE;
-        preempt_enable();
        local_irq_enable();
+        preempt_enable();
        while (!guest_state_valid(vcpu)) {
                err = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
@@ -3168,7 +3168,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
                if (err != EMULATE_DONE) {
                        kvm_report_emulation_failure(vcpu, "emulation failure");
-                        return;
+                        break;
                }
                if (signal_pending(current))
@@ -3177,8 +3177,8 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
                        schedule();
        }
-        local_irq_disable();
        preempt_disable();
+        local_irq_disable();
        vmx->invalid_state_emulation_result = err;
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fe5474aec41a..3d4529011828 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -704,11 +704,48 @@ static bool msr_mtrr_valid(unsigned msr)
        return false;
 }
+static bool valid_pat_type(unsigned t)
+{
+        return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */
+}
+static bool valid_mtrr_type(unsigned t)
+{
+        return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
+}
+static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+        int i;
+        if (!msr_mtrr_valid(msr))
+                return false;
+        if (msr == MSR_IA32_CR_PAT) {
+                for (i = 0; i < 8; i++)
+                        if (!valid_pat_type((data >> (i * 8)) & 0xff))
+                                return false;
+                return true;
+        } else if (msr == MSR_MTRRdefType) {
+                if (data & ~0xcff)
+                        return false;
+                return valid_mtrr_type(data & 0xff);
+        } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) {
+                for (i = 0; i < 8 ; i++)
+                        if (!valid_mtrr_type((data >> (i * 8)) & 0xff))
+                                return false;
+                return true;
+        }
+        /* variable MTRRs */
+        return valid_mtrr_type(data & 0xff);
+}
 static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
        u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
-        if (!msr_mtrr_valid(msr))
+        if (!mtrr_valid(vcpu, msr, data))
                return 1;
        if (msr == MSR_MTRRdefType) {
@@ -1079,14 +1116,13 @@ long kvm_arch_dev_ioctl(struct file *filp,
                if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
                        goto out;
                r = -E2BIG;
-                if (n < num_msrs_to_save)
+                if (n < msr_list.nmsrs)
                        goto out;
                r = -EFAULT;
                if (copy_to_user(user_msr_list->indices, &msrs_to_save,
                                 num_msrs_to_save * sizeof(u32)))
                        goto out;
-                if (copy_to_user(user_msr_list->indices
+                if (copy_to_user(user_msr_list->indices + num_msrs_to_save,
-                                 + num_msrs_to_save * sizeof(u32),
                                 &emulated_msrs,
                                 ARRAY_SIZE(emulated_msrs) * sizeof(u32)))
                        goto out;