Merge branch 'master' of /repos/git/net-next-2.6

Conflicts:
	Documentation/feature-removal-schedule.txt
	net/ipv6/netfilter/ip6t_REJECT.c
	net/netfilter/xt_limit.c

Signed-off-by: Patrick McHardy <kaber@trash.net>

106 files changed, 512 insertions, 271 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0eacb1ffb42..9458685902b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1216,8 +1216,8 @@ config NUMA_EMU
 
 config NODES_SHIFT
 	int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
-	range 1 9
-	default "9" if MAXSMP
+	range 1 10
+	default "10" if MAXSMP
 	default "6" if X86_64
 	default "4" if X86_NUMAQ
 	default "3"
diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c
index daef6cd2b45..1a8f8649c03 100644
--- a/arch/x86/crypto/fpu.c
+++ b/arch/x86/crypto/fpu.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <asm/i387.h>
 
 struct crypto_fpu_ctx {
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 280c019cfad..0350311906a 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -21,7 +21,6 @@
 #include <linux/fcntl.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
-#include <linux/slab.h>
 #include <linux/binfmts.h>
 #include <linux/personality.h>
 #include <linux/init.h>
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 74c35431b7d..626be156d88 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -40,6 +40,7 @@
 #include <linux/ptrace.h>
 #include <linux/highuid.h>
 #include <linux/sysctl.h>
+#include <linux/slab.h>
 #include <asm/mman.h>
 #include <asm/types.h>
 #include <asm/uaccess.h>
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 635f03bb499..d07b44f7d1d 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -82,6 +82,9 @@ enum fixed_addresses {
 #endif
 	FIX_DBGP_BASE,
 	FIX_EARLYCON_MEM_BASE,
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+	FIX_OHCI1394_BASE,
+#endif
 #ifdef CONFIG_X86_LOCAL_APIC
 	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
 #endif
@@ -132,9 +135,6 @@ enum fixed_addresses {
 	   (__end_of_permanent_fixed_addresses & (TOTAL_FIX_BTMAPS - 1))
 	 : __end_of_permanent_fixed_addresses,
 	FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
-	FIX_OHCI1394_BASE,
-#endif
 #ifdef CONFIG_X86_32
 	FIX_WP_TEST,
 #endif
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index a929c9ede33..46c0fe05f23 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -133,6 +133,7 @@ extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
 
 typedef int vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
+extern void setup_vector_irq(int cpu);
 
 #ifdef CONFIG_X86_IO_APIC
 extern void lock_vector_lock(void);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1cd58cdbc03..4604e6a54d3 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -105,6 +105,8 @@
 #define MSR_AMD64_PATCH_LEVEL		0x0000008b
 #define MSR_AMD64_NB_CFG		0xc001001f
 #define MSR_AMD64_PATCH_LOADER		0xc0010020
+#define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
+#define MSR_AMD64_OSVW_STATUS		0xc0010141
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030
 #define MSR_AMD64_IBSFETCHLINAD		0xc0011031
 #define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 47339a1ac7b..2984a25ff38 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -19,7 +19,6 @@
 #include <asm/paravirt.h>
 
 #include <linux/bitops.h>
-#include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 0061ea26306..cd40aba6aa9 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -31,6 +31,7 @@
 #include <linux/module.h>
 #include <linux/dmi.h>
 #include <linux/irq.h>
+#include <linux/slab.h>
 #include <linux/bootmem.h>
 #include <linux/ioport.h>
 #include <linux/pci.h>
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 3a4bf35c179..1a160d5d44d 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -8,6 +8,7 @@
 #include <linux/vmalloc.h>
 #include <linux/memory.h>
 #include <linux/stop_machine.h>
+#include <linux/slab.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index adb0ba02570..f3dadb571d9 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -18,8 +18,8 @@
  */
 
 #include <linux/pci.h>
-#include <linux/gfp.h>
 #include <linux/bitmap.h>
+#include <linux/slab.h>
 #include <linux/debugfs.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-mapping.h>
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 9dc91b43147..42f5350b908 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -19,8 +19,8 @@
 
 #include <linux/pci.h>
 #include <linux/acpi.h>
-#include <linux/gfp.h>
 #include <linux/list.h>
+#include <linux/slab.h>
 #include <linux/sysdev.h>
 #include <linux/interrupt.h>
 #include <linux/msi.h>
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 4b7099526d2..ff469e47005 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -33,6 +33,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/sysdev.h>
+#include <linux/slab.h>
 #include <linux/pm.h>
 #include <linux/pci.h>
 #include <linux/sfi.h>
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 00187f1fcfb..e5a4a1e0161 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1640,8 +1640,10 @@ int __init APIC_init_uniprocessor(void)
 	}
 #endif
 
+#ifndef CONFIG_SMP
 	enable_IR_x2apic();
 	default_setup_apic_routing();
+#endif
 
 	verify_local_APIC();
 	connect_bsp_APIC();
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index dd2b5f26464..03ba1b895f5 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -42,6 +42,7 @@
 #include <linux/errno.h>
 #include <linux/acpi.h>
 #include <linux/init.h>
+#include <linux/gfp.h>
 #include <linux/nmi.h>
 #include <linux/smp.h>
 #include <linux/io.h>
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index e4e0ddcb154..127b8718abf 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -36,6 +36,7 @@
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/jiffies.h>	/* time_after() */
+#include <linux/slab.h>
 #ifdef CONFIG_ACPI
 #include <acpi/acpi_bus.h>
 #endif
@@ -1268,6 +1269,14 @@ void __setup_vector_irq(int cpu)
 	/* Mark the inuse vectors */
 	for_each_irq_desc(irq, desc) {
 		cfg = desc->chip_data;
+
+		/*
+		 * If it is a legacy IRQ handled by the legacy PIC, this cpu
+		 * will be part of the irq_cfg's domain.
+		 */
+		if (irq < legacy_pic->nr_legacy_irqs && !IO_APIC_IRQ(irq))
+			cpumask_set_cpu(cpu, cfg->domain);
+
 		if (!cpumask_test_cpu(cpu, cfg->domain))
 			continue;
 		vector = cfg->vector;
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index 8aa65adbd25..1edaf15c0b8 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -18,6 +18,7 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/sysdev.h>
 #include <linux/sysctl.h>
 #include <linux/percpu.h>
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 49dbeaef2a2..c085d52dbaf 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -17,6 +17,7 @@
 #include <linux/ctype.h>
 #include <linux/sched.h>
 #include <linux/timer.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/init.h>
 #include <linux/io.h>
diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c
index 30f25a75fe2..5de7f4c5697 100644
--- a/arch/x86/kernel/bootflag.c
+++ b/arch/x86/kernel/bootflag.c
@@ -5,7 +5,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/string.h>
-#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/acpi.h>
 #include <asm/io.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 1b1920fa7c8..459168083b7 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -33,6 +33,7 @@
 #include <linux/cpufreq.h>
 #include <linux/compiler.h>
 #include <linux/dmi.h>
+#include <linux/slab.h>
 #include <trace/events/power.h>
 
 #include <linux/acpi.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/elanfreq.c b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
index 006b278b0d5..c587db472a7 100644
--- a/arch/x86/kernel/cpu/cpufreq/elanfreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
@@ -20,7 +20,6 @@
 #include <linux/module.h>
 #include <linux/init.h>
 
-#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/cpufreq.h>
 
diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
index ac27ec2264d..16e3483be9e 100644
--- a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
@@ -80,6 +80,7 @@
 #include <linux/cpufreq.h>
 #include <linux/pci.h>
 #include <linux/errno.h>
+#include <linux/slab.h>
 
 #include <asm/processor-cyrix.h>
 
diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c
index da5f70fcb76..e7b559d74c5 100644
--- a/arch/x86/kernel/cpu/cpufreq/longrun.c
+++ b/arch/x86/kernel/cpu/cpufreq/longrun.c
@@ -9,7 +9,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/cpufreq.h>
 #include <linux/timex.h>
 
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 86961519372..7b8a8ba67b0 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -25,7 +25,6 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/cpufreq.h>
-#include <linux/slab.h>
 #include <linux/cpumask.h>
 #include <linux/timex.h>
 
diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
index ff36d2979a9..ce7cde713e7 100644
--- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
@@ -30,6 +30,7 @@
 #include <linux/sched.h>
 #include <linux/cpufreq.h>
 #include <linux/compiler.h>
+#include <linux/slab.h>
 
 #include <linux/acpi.h>
 #include <linux/io.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
index cb01dac267d..b3379d6a5c5 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
@@ -13,7 +13,6 @@
 #include <linux/init.h>
 #include <linux/cpufreq.h>
 #include <linux/ioport.h>
-#include <linux/slab.h>
 #include <linux/timex.h>
 #include <linux/io.h>
 
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index 8d672ef162c..9b1ff37de46 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -20,6 +20,7 @@
 #include <linux/sched.h>	/* current */
 #include <linux/delay.h>
 #include <linux/compiler.h>
+#include <linux/gfp.h>
 
 #include <asm/msr.h>
 #include <asm/processor.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index 2ce8e0b5cc5..561758e9518 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -23,7 +23,6 @@
 #include <linux/init.h>
 #include <linux/cpufreq.h>
 #include <linux/pci.h>
-#include <linux/slab.h>
 #include <linux/sched.h>
 
 #include "speedstep-lib.h"
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
index ad0083abfa2..a94ec6be69f 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
@@ -13,7 +13,6 @@
 #include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/cpufreq.h>
-#include <linux/slab.h>
 
 #include <asm/msr.h>
 #include <asm/tsc.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
index 04d73c114e4..8abd869baab 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
@@ -17,7 +17,6 @@
 #include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/cpufreq.h>
-#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <asm/ist.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 73734baa50f..e7dbde7bfed 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -22,6 +22,7 @@
 #include <linux/kdebug.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#include <linux/gfp.h>
 #include <asm/mce.h>
 #include <asm/apic.h>
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3ab9c886b61..8a6f0afa767 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -26,6 +26,7 @@
 #include <linux/sched.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/kmod.h>
 #include <linux/poll.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index cda932ca3ad..224392d8fe8 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -21,6 +21,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sysfs.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index d15df6e49bf..62b48e40920 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -5,6 +5,7 @@
  * Author: Andi Kleen
  */
 
+#include <linux/gfp.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/percpu.h>
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 9aa5dc76ff4..fd31a441c61 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -6,7 +6,6 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/io.h>
 #include <linux/mm.h>
 
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index e006e56f699..79289632cb2 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -5,6 +5,7 @@
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/string.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 
 #define LINE_SIZE 80
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 42aafd11e17..db5bdc8addf 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -21,6 +21,7 @@
 #include <linux/kdebug.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
+#include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/cpu.h>
 #include <linux/bitops.h>
@@ -28,6 +29,7 @@
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
 #include <asm/nmi.h>
+#include <asm/compat.h>
 
 static u64 perf_event_mask __read_mostly;
 
@@ -133,8 +135,8 @@ struct x86_pmu {
 	int		(*handle_irq)(struct pt_regs *);
 	void		(*disable_all)(void);
 	void		(*enable_all)(void);
-	void		(*enable)(struct hw_perf_event *, int);
-	void		(*disable)(struct hw_perf_event *, int);
+	void		(*enable)(struct perf_event *);
+	void		(*disable)(struct perf_event *);
 	unsigned	eventsel;
 	unsigned	perfctr;
 	u64		(*event_map)(int);
@@ -157,6 +159,11 @@ struct x86_pmu {
 	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
 	struct event_constraint *event_constraints;
+
+	int		(*cpu_prepare)(int cpu);
+	void		(*cpu_starting)(int cpu);
+	void		(*cpu_dying)(int cpu);
+	void		(*cpu_dead)(int cpu);
 };
 
 static struct x86_pmu x86_pmu __read_mostly;
@@ -165,8 +172,7 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
 	.enabled = 1,
 };
 
-static int x86_perf_event_set_period(struct perf_event *event,
-			     struct hw_perf_event *hwc, int idx);
+static int x86_perf_event_set_period(struct perf_event *event);
 
 /*
  * Generalized hw caching related hw_event table, filled
@@ -189,11 +195,12 @@ static u64 __read_mostly hw_cache_event_ids
  * Returns the delta events processed.
  */
 static u64
-x86_perf_event_update(struct perf_event *event,
-			struct hw_perf_event *hwc, int idx)
+x86_perf_event_update(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	int shift = 64 - x86_pmu.event_bits;
 	u64 prev_raw_count, new_raw_count;
+	int idx = hwc->idx;
 	s64 delta;
 
 	if (idx == X86_PMC_IDX_FIXED_BTS)
@@ -293,7 +300,7 @@ static inline bool bts_available(void)
 	return x86_pmu.enable_bts != NULL;
 }
 
-static inline void init_debug_store_on_cpu(int cpu)
+static void init_debug_store_on_cpu(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
 
@@ -305,7 +312,7 @@ static inline void init_debug_store_on_cpu(int cpu)
 		     (u32)((u64)(unsigned long)ds >> 32));
 }
 
-static inline void fini_debug_store_on_cpu(int cpu)
+static void fini_debug_store_on_cpu(int cpu)
 {
 	if (!per_cpu(cpu_hw_events, cpu).ds)
 		return;
@@ -638,7 +645,7 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 		if (test_bit(hwc->idx, used_mask))
 			break;
 
-		set_bit(hwc->idx, used_mask);
+		__set_bit(hwc->idx, used_mask);
 		if (assign)
 			assign[i] = hwc->idx;
 	}
@@ -687,7 +694,7 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 			if (j == X86_PMC_IDX_MAX)
 				break;
 
-			set_bit(j, used_mask);
+			__set_bit(j, used_mask);
 
 			if (assign)
 				assign[i] = j;
@@ -780,6 +787,7 @@ static inline int match_prev_assignment(struct hw_perf_event *hwc,
 		hwc->last_tag == cpuc->tags[i];
 }
 
+static int x86_pmu_start(struct perf_event *event);
 static void x86_pmu_stop(struct perf_event *event);
 
 void hw_perf_enable(void)
@@ -796,6 +804,7 @@ void hw_perf_enable(void)
 		return;
 
 	if (cpuc->n_added) {
+		int n_running = cpuc->n_events - cpuc->n_added;
 		/*
 		 * apply assignment obtained either from
 		 * hw_perf_group_sched_in() or x86_pmu_enable()
@@ -803,8 +812,7 @@ void hw_perf_enable(void)
 		 * step1: save events moving to new counters
 		 * step2: reprogram moved events into new counters
 		 */
-		for (i = 0; i < cpuc->n_events; i++) {
-
+		for (i = 0; i < n_running; i++) {
 			event = cpuc->event_list[i];
 			hwc = &event->hw;
 
@@ -819,29 +827,18 @@ void hw_perf_enable(void)
 				continue;
 
 			x86_pmu_stop(event);
-
-			hwc->idx = -1;
 		}
 
 		for (i = 0; i < cpuc->n_events; i++) {
-
 			event = cpuc->event_list[i];
 			hwc = &event->hw;
 
-			if (hwc->idx == -1) {
+			if (!match_prev_assignment(hwc, cpuc, i))
 				x86_assign_hw_event(event, cpuc, i);
-				x86_perf_event_set_period(event, hwc, hwc->idx);
-			}
-			/*
-			 * need to mark as active because x86_pmu_disable()
-			 * clear active_mask and events[] yet it preserves
-			 * idx
-			 */
-			set_bit(hwc->idx, cpuc->active_mask);
-			cpuc->events[hwc->idx] = event;
+			else if (i < n_running)
+				continue;
 
-			x86_pmu.enable(hwc, hwc->idx);
-			perf_event_update_userpage(event);
+			x86_pmu_start(event);
 		}
 		cpuc->n_added = 0;
 		perf_events_lapic_init();
@@ -853,15 +850,16 @@ void hw_perf_enable(void)
 	x86_pmu.enable_all();
 }
 
-static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc)
 {
-	(void)checking_wrmsrl(hwc->config_base + idx,
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
 			      hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
-static inline void x86_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+static inline void x86_pmu_disable_event(struct perf_event *event)
 {
-	(void)checking_wrmsrl(hwc->config_base + idx, hwc->config);
+	struct hw_perf_event *hwc = &event->hw;
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx, hwc->config);
 }
 
 static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
@@ -871,12 +869,12 @@ static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
  * To be called with the event disabled in hw:
  */
 static int
-x86_perf_event_set_period(struct perf_event *event,
-			     struct hw_perf_event *hwc, int idx)
+x86_perf_event_set_period(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	s64 left = atomic64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
-	int err, ret = 0;
+	int err, ret = 0, idx = hwc->idx;
 
 	if (idx == X86_PMC_IDX_FIXED_BTS)
 		return 0;
@@ -922,11 +920,11 @@ x86_perf_event_set_period(struct perf_event *event,
 	return ret;
 }
 
-static void x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void x86_pmu_enable_event(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	if (cpuc->enabled)
-		__x86_pmu_enable_event(hwc, idx);
+		__x86_pmu_enable_event(&event->hw);
 }
 
 /*
@@ -962,34 +960,32 @@ static int x86_pmu_enable(struct perf_event *event)
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
 	cpuc->n_events = n;
-	cpuc->n_added  = n - n0;
+	cpuc->n_added += n - n0;
 
 	return 0;
 }
 
 static int x86_pmu_start(struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx = event->hw.idx;
 
-	if (hwc->idx == -1)
+	if (idx == -1)
 		return -EAGAIN;
 
-	x86_perf_event_set_period(event, hwc, hwc->idx);
-	x86_pmu.enable(hwc, hwc->idx);
+	x86_perf_event_set_period(event);
+	cpuc->events[idx] = event;
+	__set_bit(idx, cpuc->active_mask);
+	x86_pmu.enable(event);
+	perf_event_update_userpage(event);
 
 	return 0;
 }
 
 static void x86_pmu_unthrottle(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (WARN_ON_ONCE(hwc->idx >= X86_PMC_IDX_MAX ||
-				cpuc->events[hwc->idx] != event))
-		return;
-
-	x86_pmu.enable(hwc, hwc->idx);
+	int ret = x86_pmu_start(event);
+	WARN_ON_ONCE(ret);
 }
 
 void perf_event_print_debug(void)
@@ -1049,18 +1045,16 @@ static void x86_pmu_stop(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
-	/*
-	 * Must be done before we disable, otherwise the nmi handler
-	 * could reenable again:
-	 */
-	clear_bit(idx, cpuc->active_mask);
-	x86_pmu.disable(hwc, idx);
+	if (!__test_and_clear_bit(idx, cpuc->active_mask))
+		return;
+
+	x86_pmu.disable(event);
 
 	/*
 	 * Drain the remaining delta count out of a event
 	 * that we are disabling:
 	 */
-	x86_perf_event_update(event, hwc, idx);
+	x86_perf_event_update(event);
 
 	cpuc->events[idx] = NULL;
 }
@@ -1108,7 +1102,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		event = cpuc->events[idx];
 		hwc = &event->hw;
 
-		val = x86_perf_event_update(event, hwc, idx);
+		val = x86_perf_event_update(event);
 		if (val & (1ULL << (x86_pmu.event_bits - 1)))
 			continue;
 
@@ -1118,11 +1112,11 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		handled		= 1;
 		data.period	= event->hw.last_period;
 
-		if (!x86_perf_event_set_period(event, hwc, idx))
+		if (!x86_perf_event_set_period(event))
 			continue;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			x86_pmu.disable(hwc, idx);
+			x86_pmu_stop(event);
 	}
 
 	if (handled)
@@ -1309,7 +1303,7 @@ int hw_perf_group_sched_in(struct perf_event *leader,
 	memcpy(cpuc->assign, assign, n0*sizeof(int));
 
 	cpuc->n_events  = n0;
-	cpuc->n_added   = n1;
+	cpuc->n_added  += n1;
 	ctx->nr_active += n1;
 
 	/*
@@ -1337,6 +1331,41 @@ undo:
 #include "perf_event_p6.c"
 #include "perf_event_intel.c"
 
+static int __cpuinit
+x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+	int ret = NOTIFY_OK;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+		if (x86_pmu.cpu_prepare)
+			ret = x86_pmu.cpu_prepare(cpu);
+		break;
+
+	case CPU_STARTING:
+		if (x86_pmu.cpu_starting)
+			x86_pmu.cpu_starting(cpu);
+		break;
+
+	case CPU_DYING:
+		if (x86_pmu.cpu_dying)
+			x86_pmu.cpu_dying(cpu);
+		break;
+
+	case CPU_UP_CANCELED:
+	case CPU_DEAD:
+		if (x86_pmu.cpu_dead)
+			x86_pmu.cpu_dead(cpu);
+		break;
+
+	default:
+		break;
+	}
+
+	return ret;
+}
+
 static void __init pmu_check_apic(void)
 {
 	if (cpu_has_apic)
@@ -1415,11 +1444,13 @@ void __init init_hw_perf_events(void)
 	pr_info("... max period:             %016Lx\n", x86_pmu.max_period);
 	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_events_fixed);
 	pr_info("... event mask:             %016Lx\n", perf_event_mask);
+
+	perf_cpu_notifier(x86_pmu_notifier);
 }
 
 static inline void x86_pmu_read(struct perf_event *event)
 {
-	x86_perf_event_update(event, &event->hw, event->hw.idx);
+	x86_perf_event_update(event);
 }
 
 static const struct pmu pmu = {
@@ -1601,14 +1632,42 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	return len;
 }
 
-static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+#ifdef CONFIG_COMPAT
+static inline int
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
-	unsigned long bytes;
+	/* 32-bit process in 64-bit kernel. */
+	struct stack_frame_ia32 frame;
+	const void __user *fp;
 
-	bytes = copy_from_user_nmi(frame, fp, sizeof(*frame));
+	if (!test_thread_flag(TIF_IA32))
+		return 0;
+
+	fp = compat_ptr(regs->bp);
+	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+		unsigned long bytes;
+		frame.next_frame     = 0;
+		frame.return_address = 0;
+
+		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+		if (bytes != sizeof(frame))
+			break;
 
-	return bytes == sizeof(*frame);
+		if (fp < compat_ptr(regs->sp))
+			break;
+
+		callchain_store(entry, frame.return_address);
+		fp = compat_ptr(frame.next_frame);
+	}
+	return 1;
 }
+#else
+static inline int
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+{
+    return 0;
+}
+#endif
 
 static void
 perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
@@ -1624,11 +1683,16 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
 	callchain_store(entry, PERF_CONTEXT_USER);
 	callchain_store(entry, regs->ip);
 
+	if (perf_callchain_user32(regs, entry))
+		return;
+
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+		unsigned long bytes;
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		if (!copy_stack_frame(fp, &frame))
+		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+		if (bytes != sizeof(frame))
 			break;
 
 		if ((unsigned long)fp < regs->sp)
@@ -1675,28 +1739,14 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return entry;
 }
 
-void hw_perf_event_setup_online(int cpu)
-{
-	init_debug_store_on_cpu(cpu);
-
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_AMD:
-		amd_pmu_cpu_online(cpu);
-		break;
-	default:
-		return;
-	}
-}
-
-void hw_perf_event_setup_offline(int cpu)
+void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
 {
-	init_debug_store_on_cpu(cpu);
-
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_AMD:
-		amd_pmu_cpu_offline(cpu);
-		break;
-	default:
-		return;
-	}
+	regs->ip = ip;
+	/*
+	 * perf_arch_fetch_caller_regs adds another call, we need to increment
+	 * the skip level
+	 */
+	regs->bp = rewind_frame_pointer(skip + 1);
+	regs->cs = __KERNEL_CS;
+	local_save_flags(regs->flags);
 }
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 8f3dbfda3c4..db6f7d4056e 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -137,6 +137,13 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc)
 	return (hwc->config & 0xe0) == 0xe0;
 }
 
+static inline int amd_has_nb(struct cpu_hw_events *cpuc)
+{
+	struct amd_nb *nb = cpuc->amd_nb;
+
+	return nb && nb->nb_id != -1;
+}
+
 static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 				      struct perf_event *event)
 {
@@ -147,7 +154,7 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 	/*
 	 * only care about NB events
 	 */
-	if (!(nb && amd_is_nb_event(hwc)))
+	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
 		return;
 
 	/*
@@ -214,7 +221,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	/*
 	 * if not NB event or no NB, then no constraints
 	 */
-	if (!(nb && amd_is_nb_event(hwc)))
+	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
 		return &unconstrained;
 
 	/*
@@ -271,28 +278,6 @@ done:
 	return &emptyconstraint;
 }
 
-static __initconst struct x86_pmu amd_pmu = {
-	.name			= "AMD",
-	.handle_irq		= x86_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
-	.enable_all		= x86_pmu_enable_all,
-	.enable			= x86_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
-	.eventsel		= MSR_K7_EVNTSEL0,
-	.perfctr		= MSR_K7_PERFCTR0,
-	.event_map		= amd_pmu_event_map,
-	.raw_event		= amd_pmu_raw_event,
-	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
-	.num_events		= 4,
-	.event_bits		= 48,
-	.event_mask		= (1ULL << 48) - 1,
-	.apic			= 1,
-	/* use highest bit to detect overflow */
-	.max_period		= (1ULL << 47) - 1,
-	.get_event_constraints	= amd_get_event_constraints,
-	.put_event_constraints	= amd_put_event_constraints
-};
-
 static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 {
 	struct amd_nb *nb;
@@ -309,57 +294,61 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	 * initialize all possible NB constraints
 	 */
 	for (i = 0; i < x86_pmu.num_events; i++) {
-		set_bit(i, nb->event_constraints[i].idxmsk);
+		__set_bit(i, nb->event_constraints[i].idxmsk);
 		nb->event_constraints[i].weight = 1;
 	}
 	return nb;
 }
 
-static void amd_pmu_cpu_online(int cpu)
+static int amd_pmu_cpu_prepare(int cpu)
 {
-	struct cpu_hw_events *cpu1, *cpu2;
-	struct amd_nb *nb = NULL;
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+
+	WARN_ON_ONCE(cpuc->amd_nb);
+
+	if (boot_cpu_data.x86_max_cores < 2)
+		return NOTIFY_OK;
+
+	cpuc->amd_nb = amd_alloc_nb(cpu, -1);
+	if (!cpuc->amd_nb)
+		return NOTIFY_BAD;
+
+	return NOTIFY_OK;
+}
+
+static void amd_pmu_cpu_starting(int cpu)
+{
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	struct amd_nb *nb;
 	int i, nb_id;
 
 	if (boot_cpu_data.x86_max_cores < 2)
 		return;
 
-	/*
-	 * function may be called too early in the
-	 * boot process, in which case nb_id is bogus
-	 */
 	nb_id = amd_get_nb_id(cpu);
-	if (nb_id == BAD_APICID)
-		return;
-
-	cpu1 = &per_cpu(cpu_hw_events, cpu);
-	cpu1->amd_nb = NULL;
+	WARN_ON_ONCE(nb_id == BAD_APICID);
 
 	raw_spin_lock(&amd_nb_lock);
 
 	for_each_online_cpu(i) {
-		cpu2 = &per_cpu(cpu_hw_events, i);
-		nb = cpu2->amd_nb;
-		if (!nb)
+		nb = per_cpu(cpu_hw_events, i).amd_nb;
+		if (WARN_ON_ONCE(!nb))
 			continue;
-		if (nb->nb_id == nb_id)
-			goto found;
-	}
 
-	nb = amd_alloc_nb(cpu, nb_id);
-	if (!nb) {
-		pr_err("perf_events: failed NB allocation for CPU%d\n", cpu);
-		raw_spin_unlock(&amd_nb_lock);
-		return;
+		if (nb->nb_id == nb_id) {
+			kfree(cpuc->amd_nb);
+			cpuc->amd_nb = nb;
+			break;
+		}
 	}
-found:
-	nb->refcnt++;
-	cpu1->amd_nb = nb;
+
+	cpuc->amd_nb->nb_id = nb_id;
+	cpuc->amd_nb->refcnt++;
 
 	raw_spin_unlock(&amd_nb_lock);
 }
 
-static void amd_pmu_cpu_offline(int cpu)
+static void amd_pmu_cpu_dead(int cpu)
 {
 	struct cpu_hw_events *cpuhw;
 
@@ -370,14 +359,44 @@ static void amd_pmu_cpu_offline(int cpu)
 
 	raw_spin_lock(&amd_nb_lock);
 
-	if (--cpuhw->amd_nb->refcnt == 0)
-		kfree(cpuhw->amd_nb);
+	if (cpuhw->amd_nb) {
+		struct amd_nb *nb = cpuhw->amd_nb;
+
+		if (nb->nb_id == -1 || --nb->refcnt == 0)
+			kfree(nb);
 
-	cpuhw->amd_nb = NULL;
+		cpuhw->amd_nb = NULL;
+	}
 
 	raw_spin_unlock(&amd_nb_lock);
 }
 
+static __initconst struct x86_pmu amd_pmu = {
+	.name			= "AMD",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= x86_pmu_disable_all,
+	.enable_all		= x86_pmu_enable_all,
+	.enable			= x86_pmu_enable_event,
+	.disable		= x86_pmu_disable_event,
+	.eventsel		= MSR_K7_EVNTSEL0,
+	.perfctr		= MSR_K7_PERFCTR0,
+	.event_map		= amd_pmu_event_map,
+	.raw_event		= amd_pmu_raw_event,
+	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
+	.num_events		= 4,
+	.event_bits		= 48,
+	.event_mask		= (1ULL << 48) - 1,
+	.apic			= 1,
+	/* use highest bit to detect overflow */
+	.max_period		= (1ULL << 47) - 1,
+	.get_event_constraints	= amd_get_event_constraints,
+	.put_event_constraints	= amd_put_event_constraints,
+
+	.cpu_prepare		= amd_pmu_cpu_prepare,
+	.cpu_starting		= amd_pmu_cpu_starting,
+	.cpu_dead		= amd_pmu_cpu_dead,
+};
+
 static __init int amd_pmu_init(void)
 {
 	/* Performance-monitoring supported from K7 and later: */
@@ -390,11 +409,6 @@ static __init int amd_pmu_init(void)
 	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
 	       sizeof(hw_cache_event_ids));
 
-	/*
-	 * explicitly initialize the boot cpu, other cpus will get
-	 * the cpu hotplug callbacks from smp_init()
-	 */
-	amd_pmu_cpu_online(smp_processor_id());
 	return 0;
 }
 
@@ -405,12 +419,4 @@ static int amd_pmu_init(void)
 	return 0;
 }
 
-static void amd_pmu_cpu_online(int cpu)
-{
-}
-
-static void amd_pmu_cpu_offline(int cpu)
-{
-}
-
 #endif
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 44b60c85210..9c794ac8783 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -548,9 +548,9 @@ static inline void intel_pmu_ack_status(u64 ack)
 }
 
 static inline void
-intel_pmu_disable_fixed(struct hw_perf_event *hwc, int __idx)
+intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 {
-	int idx = __idx - X86_PMC_IDX_FIXED;
+	int idx = hwc->idx - X86_PMC_IDX_FIXED;
 	u64 ctrl_val, mask;
 
 	mask = 0xfULL << (idx * 4);
@@ -621,26 +621,28 @@ static void intel_pmu_drain_bts_buffer(void)
 }
 
 static inline void
-intel_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+intel_pmu_disable_event(struct perf_event *event)
 {
-	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
 		intel_pmu_disable_bts();
 		intel_pmu_drain_bts_buffer();
 		return;
 	}
 
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_disable_fixed(hwc, idx);
+		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
-	x86_pmu_disable_event(hwc, idx);
+	x86_pmu_disable_event(event);
 }
 
 static inline void
-intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
+intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 {
-	int idx = __idx - X86_PMC_IDX_FIXED;
+	int idx = hwc->idx - X86_PMC_IDX_FIXED;
 	u64 ctrl_val, bits, mask;
 	int err;
 
@@ -670,9 +672,11 @@ intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
 	err = checking_wrmsrl(hwc->config_base, ctrl_val);
 }
 
-static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void intel_pmu_enable_event(struct perf_event *event)
 {
-	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
 		if (!__get_cpu_var(cpu_hw_events).enabled)
 			return;
 
@@ -681,11 +685,11 @@ static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
 	}
 
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_enable_fixed(hwc, idx);
+		intel_pmu_enable_fixed(hwc);
 		return;
 	}
 
-	__x86_pmu_enable_event(hwc, idx);
+	__x86_pmu_enable_event(hwc);
 }
 
 /*
@@ -694,14 +698,8 @@ static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
  */
 static int intel_pmu_save_and_restart(struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
-	int ret;
-
-	x86_perf_event_update(event, hwc, idx);
-	ret = x86_perf_event_set_period(event, hwc, idx);
-
-	return ret;
+	x86_perf_event_update(event);
+	return x86_perf_event_set_period(event);
 }
 
 static void intel_pmu_reset(void)
@@ -745,11 +743,11 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
-	perf_disable();
+	intel_pmu_disable_all();
 	intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
 	if (!status) {
-		perf_enable();
+		intel_pmu_enable_all();
 		return 0;
 	}
 
@@ -759,8 +757,7 @@ again:
 		WARN_ONCE(1, "perfevents: irq loop stuck!\n");
 		perf_event_print_debug();
 		intel_pmu_reset();
-		perf_enable();
-		return 1;
+		goto done;
 	}
 
 	inc_irq_stat(apic_perf_irqs);
@@ -768,7 +765,6 @@ again:
 	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[bit];
 
-		clear_bit(bit, (unsigned long *) &status);
 		if (!test_bit(bit, cpuc->active_mask))
 			continue;
 
@@ -778,7 +774,7 @@ again:
 		data.period = event->hw.last_period;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			intel_pmu_disable_event(&event->hw, bit);
+			x86_pmu_stop(event);
 	}
 
 	intel_pmu_ack_status(ack);
@@ -790,8 +786,8 @@ again:
 	if (status)
 		goto again;
 
-	perf_enable();
-
+done:
+	intel_pmu_enable_all();
 	return 1;
 }
 
@@ -870,7 +866,10 @@ static __initconst struct x86_pmu intel_pmu = {
 	.max_period		= (1ULL << 31) - 1,
 	.enable_bts		= intel_pmu_enable_bts,
 	.disable_bts		= intel_pmu_disable_bts,
-	.get_event_constraints	= intel_get_event_constraints
+	.get_event_constraints	= intel_get_event_constraints,
+
+	.cpu_starting		= init_debug_store_on_cpu,
+	.cpu_dying		= fini_debug_store_on_cpu,
 };
 
 static __init int intel_pmu_init(void)
@@ -937,6 +936,7 @@ static __init int intel_pmu_init(void)
 
 	case 26: /* 45 nm nehalem, "Bloomfield" */
 	case 30: /* 45 nm nehalem, "Lynnfield" */
+	case 46: /* 45 nm nehalem-ex, "Beckton" */
 		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index a4e67b99d91..a330485d14d 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -77,27 +77,29 @@ static void p6_pmu_enable_all(void)
 }
 
 static inline void
-p6_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+p6_pmu_disable_event(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
 	u64 val = P6_NOP_EVENT;
 
 	if (cpuc->enabled)
 		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
-	(void)checking_wrmsrl(hwc->config_base + idx, val);
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
 }
 
-static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void p6_pmu_enable_event(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
 	u64 val;
 
 	val = hwc->config;
 	if (cpuc->enabled)
 		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
-	(void)checking_wrmsrl(hwc->config_base + idx, val);
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
 }
 
 static __initconst struct x86_pmu p6_pmu = {
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 83e5e628de7..8b862d5900f 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -40,6 +40,7 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/uaccess.h>
+#include <linux/gfp.h>
 
 #include <asm/processor.h>
 #include <asm/msr.h>
diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c
index cd97ce18c29..67414550c3c 100644
--- a/arch/x86/kernel/crash_dump_32.c
+++ b/arch/x86/kernel/crash_dump_32.c
@@ -5,6 +5,7 @@
  *	Copyright (C) IBM Corporation, 2004. All rights reserved
  */
 
+#include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/highmem.h>
 #include <linux/crash_dump.h>
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index 4fd1420faff..e39e77168a3 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -29,4 +29,24 @@ struct stack_frame {
 	struct stack_frame *next_frame;
 	unsigned long return_address;
 };
+
+struct stack_frame_ia32 {
+    u32 next_frame;
+    u32 return_address;
+};
+
+static inline unsigned long rewind_frame_pointer(int n)
+{
+	struct stack_frame *frame;
+
+	get_bp(frame);
+
+#ifdef CONFIG_FRAME_POINTER
+	while (n--)
+		frame = frame->next_frame;
 #endif
+
+	return (unsigned long)frame;
+}
+
+#endif /* DUMPSTACK_H */
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index d5e2a2ebb62..272c9f1f05f 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -208,7 +208,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 			if (in_irq_stack(stack, irq_stack, irq_stack_end)) {
 				if (ops->stack(data, "IRQ") < 0)
 					break;
-				bp = print_context_stack(tinfo, stack, bp,
+				bp = ops->walk_stack(tinfo, stack, bp,
 					ops, data, irq_stack_end, &graph);
 				/*
 				 * We link to the next stack (which would be
@@ -229,7 +229,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	/*
 	 * This handles the process stack:
 	 */
-	bp = print_context_stack(tinfo, stack, bp, ops, data, NULL, &graph);
+	bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
 	put_cpu();
 }
 EXPORT_SYMBOL(dump_trace);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 740b440fbd7..7bca3c6a02f 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -519,29 +519,45 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
 	printk(KERN_DEBUG "e820 remove range: %016Lx - %016Lx ",
 		       (unsigned long long) start,
 		       (unsigned long long) end);
-	e820_print_type(old_type);
+	if (checktype)
+		e820_print_type(old_type);
 	printk(KERN_CONT "\n");
 
 	for (i = 0; i < e820.nr_map; i++) {
 		struct e820entry *ei = &e820.map[i];
 		u64 final_start, final_end;
+		u64 ei_end;
 
 		if (checktype && ei->type != old_type)
 			continue;
+
+		ei_end = ei->addr + ei->size;
 		/* totally covered? */
-		if (ei->addr >= start &&
-		    (ei->addr + ei->size) <= (start + size)) {
+		if (ei->addr >= start && ei_end <= end) {
 			real_removed_size += ei->size;
 			memset(ei, 0, sizeof(struct e820entry));
 			continue;
 		}
+
+		/* new range is totally covered? */
+		if (ei->addr < start && ei_end > end) {
+			e820_add_region(end, ei_end - end, ei->type);
+			ei->size = start - ei->addr;
+			real_removed_size += size;
+			continue;
+		}
+
 		/* partially covered */
 		final_start = max(start, ei->addr);
-		final_end = min(start + size, ei->addr + ei->size);
+		final_end = min(end, ei_end);
 		if (final_start >= final_end)
 			continue;
 		real_removed_size += final_end - final_start;
 
+		/*
+		 * left range could be head or tail, so need to update
+		 * size at first.
+		 */
 		ei->size -= final_end - final_start;
 		if (ei->addr < final_start)
 			continue;
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index adedeef1ded..b2e24603739 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -7,6 +7,7 @@
 
 #include <linux/init.h>
 #include <linux/start_kernel.h>
+#include <linux/mm.h>
 
 #include <asm/setup.h>
 #include <asm/sections.h>
@@ -44,9 +45,10 @@ void __init i386_start_kernel(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+		/* Assume only end is not page aligned */
 		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+		u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b5a9896ca1e..7147143fd61 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -103,9 +103,10 @@ void __init x86_64_start_reservations(char *real_mode_data)
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+		/* Assume only end is not page aligned */
 		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
-		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
+		unsigned long ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ee4fa1bfcb3..23b4ecdffa9 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -4,6 +4,7 @@
 #include <linux/sysdev.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
+#include <linux/slab.h>
 #include <linux/hpet.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
@@ -399,9 +400,15 @@ static int hpet_next_event(unsigned long delta,
 	 * then we might have a real hardware problem. We can not do
 	 * much about it here, but at least alert the user/admin with
 	 * a prominent warning.
+	 * An erratum on some chipsets (ICH9,..), results in comparator read
+	 * immediately following a write returning old value. Workaround
+	 * for this is to read this value second time, when first
+	 * read returns old value.
 	 */
-	WARN_ONCE(hpet_readl(HPET_Tn_CMP(timer)) != cnt,
+	if (unlikely((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt)) {
+		WARN_ONCE(hpet_readl(HPET_Tn_CMP(timer)) != cnt,
 		  KERN_WARNING "hpet: compare register read back failed.\n");
+	}
 
 	return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
 }
@@ -1143,6 +1150,7 @@ int hpet_set_periodic_freq(unsigned long freq)
 		do_div(clc, freq);
 		clc >>= hpet_clockevent.shift;
 		hpet_pie_delta = clc;
+		hpet_pie_limit = 0;
 	}
 	return 1;
 }
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index c01a2b846d4..54c31c28548 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/regset.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 #include <asm/sigcontext.h>
 #include <asm/processor.h>
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index fb725ee15f5..7c9f02c130f 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -5,7 +5,6 @@
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/timex.h>
-#include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/init.h>
 #include <linux/kernel_stat.h>
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index ef257fc2921..0ed2d300cd4 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -5,7 +5,6 @@
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/timex.h>
-#include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/kprobes.h>
 #include <linux/init.h>
@@ -141,6 +140,28 @@ void __init init_IRQ(void)
 	x86_init.irqs.intr_init();
 }
 
+/*
+ * Setup the vector to irq mappings.
+ */
+void setup_vector_irq(int cpu)
+{
+#ifndef CONFIG_X86_IO_APIC
+	int irq;
+
+	/*
+	 * On most of the platforms, legacy PIC delivers the interrupts on the
+	 * boot cpu. But there are certain platforms where PIC interrupts are
+	 * delivered to multiple cpu's. If the legacy IRQ is handled by the
+	 * legacy PIC, for the new cpu that is coming online, setup the static
+	 * legacy vector to irq mapping:
+	 */
+	for (irq = 0; irq < legacy_pic->nr_legacy_irqs; irq++)
+		per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
+#endif
+
+	__setup_vector_irq(cpu);
+}
+
 static void __init smp_intr_init(void)
 {
 #ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/k8.c
index 9b895464dd0..0f7bc20cfcd 100644
--- a/arch/x86/kernel/k8.c
+++ b/arch/x86/kernel/k8.c
@@ -2,8 +2,8 @@
  * Shared support code for AMD K8 northbridges and derivates.
  * Copyright 2006 Andi Kleen, SUSE Labs. Subject to GPLv2.
  */
-#include <linux/gfp.h>
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/module.h>
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index e444357375c..8afd9f321f1 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -9,6 +9,7 @@
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/stat.h>
 #include <linux/io.h>
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index bfba6019d76..b2258ca9100 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -618,8 +618,8 @@ int kgdb_arch_init(void)
 	 * portion of kgdb because this operation requires mutexs to
 	 * complete.
 	 */
+	hw_breakpoint_init(&attr);
 	attr.bp_addr = (unsigned long)kgdb_arch_init;
-	attr.type = PERF_TYPE_BREAKPOINT;
 	attr.bp_len = HW_BREAKPOINT_LEN_1;
 	attr.bp_type = HW_BREAKPOINT_W;
 	attr.disabled = 1;
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ec6ef60cbd1..ea697263b37 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/errno.h>
+#include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/mm.h>
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 4a8bb82248a..035c8c52918 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/kexec.h>
 #include <linux/string.h>
+#include <linux/gfp.h>
 #include <linux/reboot.h>
 #include <linux/numa.h>
 #include <linux/ftrace.h>
diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c
index 845d80ce1ef..63eaf659623 100644
--- a/arch/x86/kernel/mca_32.c
+++ b/arch/x86/kernel/mca_32.c
@@ -42,6 +42,7 @@
 #include <linux/kernel.h>
 #include <linux/mca.h>
 #include <linux/kprobes.h>
+#include <linux/slab.h>
 #include <asm/system.h>
 #include <asm/io.h>
 #include <linux/proc_fs.h>
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 89f386f044e..e0bc186d750 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/bug.h>
 #include <linux/mm.h>
+#include <linux/gfp.h>
 
 #include <asm/system.h>
 #include <asm/page.h>
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index a2c1edd2d3a..e81030f71a8 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -664,7 +664,7 @@ static void __init smp_reserve_memory(struct mpf_intel *mpf)
 {
 	unsigned long size = get_mpc_size(mpf->physptr);
 
-	reserve_early(mpf->physptr, mpf->physptr+size, "MP-table mpc");
+	reserve_early_overlap_ok(mpf->physptr, mpf->physptr+size, "MP-table mpc");
 }
 
 static int __init smp_scan_config(unsigned long base, unsigned long length)
@@ -693,7 +693,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
 			       mpf, (u64)virt_to_phys(mpf));
 
 			mem = virt_to_phys(mpf);
-			reserve_early(mem, mem + sizeof(*mpf), "MP-table mpf");
+			reserve_early_overlap_ok(mem, mem + sizeof(*mpf), "MP-table mpf");
 			if (mpf->physptr)
 				smp_reserve_memory(mpf);
 
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 206735ac8cb..4d4468e9f47 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -37,6 +37,7 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/uaccess.h>
+#include <linux/gfp.h>
 
 #include <asm/processor.h>
 #include <asm/msr.h>
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index a4ac764a688..4b7e3d8b01d 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -2,6 +2,7 @@
 #include <linux/dma-debug.h>
 #include <linux/dmar.h>
 #include <linux/bootmem.h>
+#include <linux/gfp.h>
 #include <linux/pci.h>
 #include <linux/kmemleak.h>
 
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index f3af115a573..68cd24f9dea 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -29,6 +29,7 @@
 #include <linux/iommu-helper.h>
 #include <linux/sysdev.h>
 #include <linux/io.h>
+#include <linux/gfp.h>
 #include <asm/atomic.h>
 #include <asm/mtrr.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 22be12b60a8..3af4af810c0 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -4,6 +4,7 @@
 #include <linux/scatterlist.h>
 #include <linux/string.h>
 #include <linux/init.h>
+#include <linux/gfp.h>
 #include <linux/pci.h>
 #include <linux/mm.h>
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ad9540676fc..28ad9f4d8b9 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -526,21 +526,37 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
 }
 
 /*
- * Check for AMD CPUs, which have potentially C1E support
+ * Check for AMD CPUs, where APIC timer interrupt does not wake up CPU from C1e.
+ * For more information see
+ * - Erratum #400 for NPT family 0xf and family 0x10 CPUs
+ * - Erratum #365 for family 0x11 (not affected because C1e not in use)
  */
 static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
 {
+	u64 val;
 	if (c->x86_vendor != X86_VENDOR_AMD)
-		return 0;
-
-	if (c->x86 < 0x0F)
-		return 0;
+		goto no_c1e_idle;
 
 	/* Family 0x0f models < rev F do not have C1E */
-	if (c->x86 == 0x0f && c->x86_model < 0x40)
-		return 0;
+	if (c->x86 == 0x0F && c->x86_model >= 0x40)
+		return 1;
 
-	return 1;
+	if (c->x86 == 0x10) {
+		/*
+		 * check OSVW bit for CPUs that are not affected
+		 * by erratum #400
+		 */
+		rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val);
+		if (val >= 2) {
+			rdmsrl(MSR_AMD64_OSVW_STATUS, val);
+			if (!(val & BIT(1)))
+				goto no_c1e_idle;
+		}
+		return 1;
+	}
+
+no_c1e_idle:
+	return 0;
 }
 
 static cpumask_var_t c1e_mask;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index a503b1fd04e..2e9b55027b7 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -12,6 +12,7 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
+#include <linux/slab.h>
 #include <linux/ptrace.h>
 #include <linux/regset.h>
 #include <linux/tracehook.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 5d7ba1a449b..c4851eff57b 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -55,7 +55,6 @@
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
-#include <linux/slab.h>
 #include <linux/user.h>
 #include <linux/delay.h>
 
@@ -314,16 +313,17 @@ static void __init reserve_brk(void)
 #define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
 static void __init relocate_initrd(void)
 {
-
+	/* Assume only end is not page aligned */
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 area_size     = PAGE_ALIGN(ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 	u64 ramdisk_here;
 	unsigned long slop, clen, mapaddr;
 	char *p, *q;
 
 	/* We need to move the initrd down into lowmem */
-	ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
+	ramdisk_here = find_e820_area(0, end_of_lowmem, area_size,
 					 PAGE_SIZE);
 
 	if (ramdisk_here == -1ULL)
@@ -332,7 +332,7 @@ static void __init relocate_initrd(void)
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
+	reserve_early(ramdisk_here, ramdisk_here + area_size,
 			 "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
@@ -376,9 +376,10 @@ static void __init relocate_initrd(void)
 
 static void __init reserve_initrd(void)
 {
+	/* Assume only end is not page aligned */
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-	u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 
 	if (!boot_params.hdr.type_of_loader ||
@@ -606,6 +607,16 @@ static int __init setup_elfcorehdr(char *arg)
 early_param("elfcorehdr", setup_elfcorehdr);
 #endif
 
+static __init void reserve_ibft_region(void)
+{
+	unsigned long addr, size = 0;
+
+	addr = find_ibft_region(&size);
+
+	if (size)
+		reserve_early_overlap_ok(addr, addr + size, "ibft");
+}
+
 #ifdef CONFIG_X86_RESERVE_LOW_64K
 static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
 {
@@ -908,6 +919,8 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	find_smp_config();
 
+	reserve_ibft_region();
+
 	reserve_trampoline_memory();
 
 #ifdef CONFIG_ACPI_SLEEP
@@ -975,8 +988,6 @@ void __init setup_arch(char **cmdline_p)
 
 	dma32_reserve_bootmem();
 
-	reserve_ibft_region();
-
 #ifdef CONFIG_KVM_CLOCK
 	kvmclock_init();
 #endif
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index ec1de97600e..d801210945d 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -21,6 +21,7 @@
 #include <linux/cache.h>
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
+#include <linux/gfp.h>
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a02e80c3c54..763d815e27a 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -49,6 +49,7 @@
 #include <linux/nmi.h>
 #include <linux/tboot.h>
 #include <linux/stackprotector.h>
+#include <linux/gfp.h>
 
 #include <asm/acpi.h>
 #include <asm/desc.h>
@@ -242,12 +243,10 @@ static void __cpuinit smp_callin(void)
 	end_local_APIC_setup();
 	map_cpu_to_logical_apicid();
 
-	notify_cpu_starting(cpuid);
-
 	/*
 	 * Need to setup vector mappings before we enable interrupts.
 	 */
-	__setup_vector_irq(smp_processor_id());
+	setup_vector_irq(smp_processor_id());
 	/*
 	 * Get our bogomips.
 	 *
@@ -264,6 +263,8 @@ static void __cpuinit smp_callin(void)
 	 */
 	smp_store_cpu_info(cpuid);
 
+	notify_cpu_starting(cpuid);
+
 	/*
 	 * Allow the master to continue.
 	 */
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 364d015efeb..17b03dd3a6b 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -9,6 +9,7 @@
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 
 #include <asm/mmu_context.h>
 #include <asm/uv/uv.h>
diff --git a/arch/x86/kernel/uv_irq.c b/arch/x86/kernel/uv_irq.c
index ece73d8e324..1d40336b030 100644
--- a/arch/x86/kernel/uv_irq.c
+++ b/arch/x86/kernel/uv_irq.c
@@ -10,6 +10,7 @@
 
 #include <linux/module.h>
 #include <linux/rbtree.h>
+#include <linux/slab.h>
 #include <linux/irq.h>
 
 #include <asm/apic.h>
diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c
index 2b75ef638db..56e421bc379 100644
--- a/arch/x86/kernel/uv_time.c
+++ b/arch/x86/kernel/uv_time.c
@@ -19,6 +19,7 @@
  *  Copyright (c) Dimitri Sivanich
  */
 #include <linux/clockchips.h>
+#include <linux/slab.h>
 
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 7dd599deca4..ce9fbacb752 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -28,6 +28,7 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/sched.h>
+#include <linux/gfp.h>
 #include <asm/vmi.h>
 #include <asm/io.h>
 #include <asm/fixmap.h>
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 44879df5569..2cc249718c4 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -291,8 +291,8 @@ SECTIONS
 	.smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
 		__smp_locks = .;
 		*(.smp_locks)
-		__smp_locks_end = .;
 		. = ALIGN(PAGE_SIZE);
+		__smp_locks_end = .;
 	}
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 294698b6daf..0150affad25 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -32,6 +32,7 @@
 #define pr_fmt(fmt) "pit: " fmt
 
 #include <linux/kvm_host.h>
+#include <linux/slab.h>
 
 #include "irq.h"
 #include "i8254.h"
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 07771da85de..a790fa128a9 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -26,6 +26,7 @@
  *   Port from Qemu.
  */
 #include <linux/mm.h>
+#include <linux/slab.h>
 #include <linux/bitops.h>
 #include "irq.h"
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4b224f90087..1eb7a4ae0c9 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -26,6 +26,7 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/math64.h>
+#include <linux/slab.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
 #include <asm/page.h>
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 741373e8ca7..48aeee8eefb 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -31,6 +31,7 @@
 #include <linux/hugetlb.h>
 #include <linux/compiler.h>
 #include <linux/srcu.h>
+#include <linux/slab.h>
 
 #include <asm/page.h>
 #include <asm/cmpxchg.h>
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 52f78dd0301..445c59411ed 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -26,6 +26,7 @@
 #include <linux/highmem.h>
 #include <linux/sched.h>
 #include <linux/ftrace_event.h>
+#include <linux/slab.h>
 
 #include <asm/desc.h>
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 14873b9f843..686492ed307 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -26,6 +26,7 @@
 #include <linux/sched.h>
 #include <linux/moduleparam.h>
 #include <linux/ftrace_event.h>
+#include <linux/slab.h>
 #include "kvm_cache_regs.h"
 #include "x86.h"
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e46282a5656..24cd0ee896e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -39,6 +39,7 @@
 #include <linux/cpufreq.h>
 #include <linux/user-return-notifier.h>
 #include <linux/srcu.h>
+#include <linux/slab.h>
 #include <trace/events/kvm.h>
 #undef TRACE_INCLUDE_FILE
 #define CREATE_TRACE_POINTS
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index f46c340727b..069ce7c37c0 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -9,7 +9,6 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
-#include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/sysctl.h>
 #include <asm/mman.h>
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index e71c5cbc8f3..b278535b14a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1,3 +1,4 @@
+#include <linux/gfp.h>
 #include <linux/initrd.h>
 #include <linux/ioport.h>
 #include <linux/swap.h>
@@ -331,11 +332,23 @@ int devmem_is_allowed(unsigned long pagenr)
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
-	unsigned long addr = begin;
+	unsigned long addr;
+	unsigned long begin_aligned, end_aligned;
 
-	if (addr >= end)
+	/* Make sure boundaries are page aligned */
+	begin_aligned = PAGE_ALIGN(begin);
+	end_aligned   = end & PAGE_MASK;
+
+	if (WARN_ON(begin_aligned != begin || end_aligned != end)) {
+		begin = begin_aligned;
+		end   = end_aligned;
+	}
+
+	if (begin >= end)
 		return;
 
+	addr = begin;
+
 	/*
 	 * If debugging page accesses then do not free this memory but
 	 * mark them not present - any buggy init-section access will
@@ -343,7 +356,7 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	 */
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
-		begin, PAGE_ALIGN(end));
+		begin, end);
 	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
 #else
 	/*
@@ -358,8 +371,7 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	for (; addr < end; addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
 		init_page_count(virt_to_page(addr));
-		memset((void *)(addr & ~(PAGE_SIZE-1)),
-			POISON_FREE_INITMEM, PAGE_SIZE);
+		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
 		free_page(addr);
 		totalram_pages++;
 	}
@@ -376,6 +388,15 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_init_pages("initrd memory", start, end);
+	/*
+	 * end could be not aligned, and We can not align that,
+	 * decompresser could be confused by aligned initrd_end
+	 * We already reserve the end partial page before in
+	 *   - i386_start_kernel()
+	 *   - x86_64_start_kernel()
+	 *   - relocate_initrd()
+	 * So here We can do PAGE_ALIGN() safely to get partial page to be freed
+	 */
+	free_init_pages("initrd memory", start, PAGE_ALIGN(end));
 }
 #endif
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 5cb3f0f54f4..bca79091b9d 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -25,11 +25,11 @@
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
-#include <linux/slab.h>
 #include <linux/proc_fs.h>
 #include <linux/memory_hotplug.h>
 #include <linux/initrd.h>
 #include <linux/cpumask.h>
+#include <linux/gfp.h>
 
 #include <asm/asm.h>
 #include <asm/bios_ebda.h>
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e9b040e1cde..ee41bba315d 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/memory_hotplug.h>
 #include <linux/nmi.h>
+#include <linux/gfp.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 536fb682336..5d0e67fff1a 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -21,6 +21,7 @@
 #include <linux/kdebug.h>
 #include <linux/mutex.h>
 #include <linux/io.h>
+#include <linux/slab.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <linux/errno.h>
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 34a3291ca10..3adff7dcc14 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -26,6 +26,7 @@
 
 #include <linux/module.h>
 #include <linux/debugfs.h>
+#include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/version.h>
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index cf07c26d9a4..28195c350b9 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -6,13 +6,13 @@
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/pfn.h>
 #include <linux/percpu.h>
+#include <linux/gfp.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index ae9648eb1c7..edc8b95afc1 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -12,7 +12,7 @@
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/gfp.h>
+#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/rbtree.h>
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index c9ba9deafe8..5c4ee422590 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -1,4 +1,5 @@
 #include <linux/mm.h>
+#include <linux/gfp.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/tlb.h>
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 46c8834aedc..1a8faf09afe 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -6,7 +6,6 @@
 #include <linux/swap.h>
 #include <linux/smp.h>
 #include <linux/highmem.h>
-#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/spinlock.h>
 #include <linux/module.h>
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 6e22454bfaa..c7b1ebfb7da 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -3,6 +3,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/dmi.h>
+#include <linux/slab.h>
 #include <asm/numa.h>
 #include <asm/pci_x86.h>
 
@@ -122,8 +123,8 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	struct acpi_resource_address64 addr;
 	acpi_status status;
 	unsigned long flags;
-	struct resource *root;
-	u64 start, end;
+	struct resource *root, *conflict;
+	u64 start, end, max_len;
 
 	status = resource_to_addr(acpi_res, &addr);
 	if (!ACPI_SUCCESS(status))
@@ -140,6 +141,17 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	} else
 		return AE_OK;
 
+	max_len = addr.maximum - addr.minimum + 1;
+	if (addr.address_length > max_len) {
+		dev_printk(KERN_DEBUG, &info->bridge->dev,
+			   "host bridge window length %#llx doesn't fit in "
+			   "%#llx-%#llx, trimming\n",
+			   (unsigned long long) addr.address_length,
+			   (unsigned long long) addr.minimum,
+			   (unsigned long long) addr.maximum);
+		addr.address_length = max_len;
+	}
+
 	start = addr.minimum + addr.translation_offset;
 	end = start + addr.address_length - 1;
 
@@ -157,9 +169,12 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 		return AE_OK;
 	}
 
-	if (insert_resource(root, res)) {
+	conflict = insert_resource_conflict(root, res);
+	if (conflict) {
 		dev_err(&info->bridge->dev,
-			"can't allocate host bridge window %pR\n", res);
+			"address space collision: host bridge window %pR "
+			"conflicts with %s %pR\n",
+			res, conflict->name, conflict);
 	} else {
 		pci_bus_add_resource(info->bus, res, 0);
 		info->res_num++;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 294e10cb11e..cf2e93869c4 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -9,6 +9,7 @@
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/dmi.h>
+#include <linux/slab.h>
 
 #include <asm/acpi.h>
 #include <asm/segment.h>
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index dece3eb9c90..46fd43f7910 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -127,9 +127,6 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 					continue;
 				if (!r->start ||
 				    pci_claim_resource(dev, idx) < 0) {
-					dev_info(&dev->dev,
-						 "can't reserve window %pR\n",
-						 r);
 					/*
 					 * Something is wrong with the region.
 					 * Invalidate the resource to prevent
@@ -181,8 +178,6 @@ static void __init pcibios_allocate_resources(int pass)
 					"BAR %d: reserving %pr (d=%d, p=%d)\n",
 					idx, r, disabled, pass);
 				if (pci_claim_resource(dev, idx) < 0) {
-					dev_info(&dev->dev,
-						 "can't reserve %pR\n", r);
 					/* We'll assign a new address later */
 					r->end -= r->start;
 					r->start = 0;
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 8b107521d24..5d362b5ba06 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -8,7 +8,6 @@
 #include <linux/kernel.h>
 #include <linux/pci.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/dmi.h>
 #include <linux/io.h>
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 8f3f9a50b1e..39b9ebe8f88 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -16,6 +16,7 @@
 #include <linux/sfi_acpi.h>
 #include <linux/bitmap.h>
 #include <linux/dmi.h>
+#include <linux/slab.h>
 #include <asm/e820.h>
 #include <asm/pci_x86.h>
 #include <asm/acpi.h>
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index 1c975cc9839..59a225c17b8 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -4,6 +4,7 @@
 
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
 #include <asm/pci_x86.h>
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 81197c62d5b..3769079874d 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -6,6 +6,7 @@
  * Copyright (c) 2006 Rafael J. Wysocki <rjw@sisk.pl>
  */
 
+#include <linux/gfp.h>
 #include <linux/suspend.h>
 #include <linux/bootmem.h>
 
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 65fdc86e923..d24f983ba1e 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -8,6 +8,7 @@
  * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
  */
 
+#include <linux/gfp.h>
 #include <linux/smp.h>
 #include <linux/suspend.h>
 #include <asm/proto.h>
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index b641388d828..ad47daeafa4 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -27,10 +27,17 @@ ENTRY(swsusp_arch_suspend)
 	ret
 
 ENTRY(restore_image)
+	movl	mmu_cr4_features, %ecx
 	movl	resume_pg_dir, %eax
 	subl	$__PAGE_OFFSET, %eax
 	movl	%eax, %cr3
 
+	jecxz	1f	# cr4 Pentium and higher, skip if zero
+	andl	$~(X86_CR4_PGE), %ecx
+	movl	%ecx, %cr4;  # turn off PGE
+	movl	%cr3, %eax;  # flush TLB
+	movl	%eax, %cr3
+1:
 	movl	restore_pblist, %edx
 	.p2align 4,,7
 
@@ -54,16 +61,8 @@ done:
 	movl	$swapper_pg_dir, %eax
 	subl	$__PAGE_OFFSET, %eax
 	movl	%eax, %cr3
-	/* Flush TLB, including "global" things (vmalloc) */
 	movl	mmu_cr4_features, %ecx
 	jecxz	1f	# cr4 Pentium and higher, skip if zero
-	movl	%ecx, %edx
-	andl	$~(X86_CR4_PGE), %edx
-	movl	%edx, %cr4;  # turn off PGE
-1:
-	movl	%cr3, %eax;  # flush TLB
-	movl	%eax, %cr3
-	jecxz	1f	# cr4 Pentium and higher, skip if zero
 	movl	%ecx, %cr4;  # turn PGE back on
 1:
 
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 21e1aeb9f3e..ac74869b814 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -6,6 +6,7 @@
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/random.h>
 #include <linux/elf.h>
diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c
index e133ce25e29..1304bcec8ee 100644
--- a/arch/x86/xen/debugfs.c
+++ b/arch/x86/xen/debugfs.c
@@ -1,5 +1,6 @@
 #include <linux/init.h>
 #include <linux/debugfs.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 
 #include "debugfs.h"
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b607239c1ba..65d8d79b46a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -28,6 +28,7 @@
 #include <linux/highmem.h>
 #include <linux/console.h>
 #include <linux/pci.h>
+#include <linux/gfp.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index f9eb7de74f4..914f04695ce 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -43,6 +43,7 @@
 #include <linux/debugfs.h>
 #include <linux/bug.h>
 #include <linux/module.h>
+#include <linux/gfp.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index deafb65ef44..a29693fd313 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -14,6 +14,7 @@
  */
 #include <linux/sched.h>
 #include <linux/err.h>
+#include <linux/slab.h>
 #include <linux/smp.h>
 
 #include <asm/paravirt.h>
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 24ded31b5ae..e0500646585 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -6,6 +6,7 @@
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/log2.h>
+#include <linux/gfp.h>
 
 #include <asm/paravirt.h>
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 0d3f07cd1b5..32764b8880b 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -13,6 +13,7 @@
 #include <linux/clockchips.h>
 #include <linux/kernel_stat.h>
 #include <linux/math64.h>
+#include <linux/gfp.h>
 
 #include <asm/pvclock.h>
 #include <asm/xen/hypervisor.h>