Merge commit 'v2.6.32-rc5' into perf/probes

Conflicts:
	kernel/trace/trace_event_profile.c

Merge reason: update to -rc5 and resolve conflict.

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

74 files changed, 577 insertions, 388 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 93698794aa3..07e01149e3b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -86,10 +86,6 @@ config STACKTRACE_SUPPORT
 config HAVE_LATENCYTOP_SUPPORT
 	def_bool y
 
-config FAST_CMPXCHG_LOCAL
-	bool
-	default y
-
 config MMU
 	def_bool y
 
@@ -432,6 +428,17 @@ config X86_NUMAQ
 	  of Flat Logical.  You will need a new lynxer.elf file to flash your
 	  firmware with - send email to <Martin.Bligh@us.ibm.com>.
 
+config X86_SUPPORTS_MEMORY_FAILURE
+	bool
+	# MCE code calls memory_failure():
+	depends on X86_MCE
+	# On 32-bit this adds too big of NODES_SHIFT and we run out of page flags:
+	depends on !X86_NUMAQ
+	# On 32-bit SPARSEMEM adds too big of SECTIONS_WIDTH:
+	depends on X86_64 || !SPARSEMEM
+	select ARCH_SUPPORTS_MEMORY_FAILURE
+	default y
+
 config X86_VISWS
 	bool "SGI 320/540 (Visual Workstation)"
 	depends on X86_32 && PCI && X86_MPPARSE && PCI_GODIRECT
@@ -484,7 +491,7 @@ if PARAVIRT_GUEST
 source "arch/x86/xen/Kconfig"
 
 config VMI
-	bool "VMI Guest support"
+	bool "VMI Guest support (DEPRECATED)"
 	select PARAVIRT
 	depends on X86_32
 	---help---
@@ -493,6 +500,15 @@ config VMI
 	  at the moment), by linking the kernel to a GPL-ed ROM module
 	  provided by the hypervisor.
 
+	  As of September 2009, VMware has started a phased retirement
+	  of this feature from VMware's products. Please see
+	  feature-removal-schedule.txt for details.  If you are
+	  planning to enable this option, please note that you cannot
+	  live migrate a VMI enabled VM to a future VMware product,
+	  which doesn't support VMI. So if you expect your kernel to
+	  seamlessly migrate to newer VMware products, keep this
+	  disabled.
+
 config KVM_CLOCK
 	bool "KVM paravirtualized clock"
 	select PARAVIRT
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 527519b8a9f..f2824fb8c79 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -400,7 +400,7 @@ config X86_TSC
 
 config X86_CMPXCHG64
 	def_bool y
-	depends on X86_PAE || X86_64
+	depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM
 
 # this should be set for all -march=.. options where the compiler
 # generates cmov.
@@ -412,6 +412,7 @@ config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
 	default "6" if X86_32 && X86_P6_NOP
+	default "5" if X86_32 && X86_CMPXCHG64
 	default "4" if X86_32 && (X86_XADD || X86_CMPXCHG || X86_BSWAP || X86_WP_WORKS_OK)
 	default "3"
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 4aefc034e9a..ba7a6df4db9 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -182,8 +182,8 @@ archclean:
 define archhelp
   echo  '* bzImage      - Compressed kernel image (arch/x86/boot/bzImage)'
   echo  '  install      - Install kernel using'
-  echo  '                  (your) ~/bin/installkernel or'
-  echo  '                  (distribution) /sbin/installkernel or'
+  echo  '                  (your) ~/bin/$(INSTALLKERNEL) or'
+  echo  '                  (distribution) /sbin/$(INSTALLKERNEL) or'
   echo  '                  install to $$(INSTALL_PATH) and run lilo'
   echo  '  fdimage      - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)'
   echo  '  fdimage144   - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)'
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 75e4f001e70..f543b70ffae 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -23,13 +23,14 @@
  */
 	.text
 
+#include <linux/init.h>
 #include <linux/linkage.h>
 #include <asm/segment.h>
 #include <asm/page_types.h>
 #include <asm/boot.h>
 #include <asm/asm-offsets.h>
 
-	.section ".text.head","ax",@progbits
+	__HEAD
 ENTRY(startup_32)
 	cld
 	/*
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index f62c284db9e..077e1b69198 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -24,6 +24,7 @@
 	.code32
 	.text
 
+#include <linux/init.h>
 #include <linux/linkage.h>
 #include <asm/segment.h>
 #include <asm/pgtable_types.h>
@@ -33,7 +34,7 @@
 #include <asm/processor-flags.h>
 #include <asm/asm-offsets.h>
 
-	.section ".text.head"
+	__HEAD
 	.code32
 ENTRY(startup_32)
 	cld
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index cc353e1b3ff..f4193bb4878 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -1,3 +1,5 @@
+#include <asm-generic/vmlinux.lds.h>
+
 OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
 
 #undef i386
@@ -18,9 +20,9 @@ SECTIONS
 	 * address 0.
 	 */
 	. = 0;
-	.text.head : {
+	.head.text : {
 		_head = . ;
-		*(.text.head)
+		HEAD_TEXT
 		_ehead = . ;
 	}
 	.rodata.compressed : {
diff --git a/arch/x86/boot/install.sh b/arch/x86/boot/install.sh
index 8d60ee15dfd..d13ec1c3864 100644
--- a/arch/x86/boot/install.sh
+++ b/arch/x86/boot/install.sh
@@ -33,8 +33,8 @@ verify "$3"
 
 # User may have a custom install script
 
-if [ -x ~/bin/${CROSS_COMPILE}installkernel ]; then exec ~/bin/${CROSS_COMPILE}installkernel "$@"; fi
-if [ -x /sbin/${CROSS_COMPILE}installkernel ]; then exec /sbin/${CROSS_COMPILE}installkernel "$@"; fi
+if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
+if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
 
 # Default install - same as make zlilo
 
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 74619c4f9fd..1733f9f65e8 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -21,8 +21,8 @@
 #define __AUDIT_ARCH_LE	   0x40000000
 
 #ifndef CONFIG_AUDITSYSCALL
-#define sysexit_audit int_ret_from_sys_call
-#define sysretl_audit int_ret_from_sys_call
+#define sysexit_audit ia32_ret_from_sys_call
+#define sysretl_audit ia32_ret_from_sys_call
 #endif
 
 #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8)
@@ -39,12 +39,12 @@
 	.endm 
 
 	/* clobbers %eax */	
-	.macro  CLEAR_RREGS _r9=rax
+	.macro  CLEAR_RREGS offset=0, _r9=rax
 	xorl 	%eax,%eax
-	movq	%rax,R11(%rsp)
-	movq	%rax,R10(%rsp)
-	movq	%\_r9,R9(%rsp)
-	movq	%rax,R8(%rsp)
+	movq	%rax,\offset+R11(%rsp)
+	movq	%rax,\offset+R10(%rsp)
+	movq	%\_r9,\offset+R9(%rsp)
+	movq	%rax,\offset+R8(%rsp)
 	.endm
 
 	/*
@@ -172,6 +172,10 @@ sysexit_from_sys_call:
 	movl	RIP-R11(%rsp),%edx		/* User %eip */
 	CFI_REGISTER rip,rdx
 	RESTORE_ARGS 1,24,1,1,1,1
+	xorq	%r8,%r8
+	xorq	%r9,%r9
+	xorq	%r10,%r10
+	xorq	%r11,%r11
 	popfq
 	CFI_ADJUST_CFA_OFFSET -8
 	/*CFI_RESTORE rflags*/
@@ -202,7 +206,7 @@ sysexit_from_sys_call:
 
 	.macro auditsys_exit exit,ebpsave=RBP
 	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10)
-	jnz int_ret_from_sys_call
+	jnz ia32_ret_from_sys_call
 	TRACE_IRQS_ON
 	sti
 	movl %eax,%esi		/* second arg, syscall return value */
@@ -218,8 +222,9 @@ sysexit_from_sys_call:
 	cli
 	TRACE_IRQS_OFF
 	testl %edi,TI_flags(%r10)
-	jnz int_with_check
-	jmp \exit
+	jz \exit
+	CLEAR_RREGS -ARGOFFSET
+	jmp int_with_check
 	.endm
 
 sysenter_auditsys:
@@ -329,6 +334,9 @@ sysretl_from_sys_call:
 	CFI_REGISTER rip,rcx
 	movl EFLAGS-ARGOFFSET(%rsp),%r11d	
 	/*CFI_REGISTER rflags,r11*/
+	xorq	%r10,%r10
+	xorq	%r9,%r9
+	xorq	%r8,%r8
 	TRACE_IRQS_ON
 	movl RSP-ARGOFFSET(%rsp),%esp
 	CFI_RESTORE rsp
@@ -353,7 +361,7 @@ cstar_tracesys:
 #endif
 	xchgl %r9d,%ebp
 	SAVE_REST
-	CLEAR_RREGS r9
+	CLEAR_RREGS 0, r9
 	movq $-ENOSYS,RAX(%rsp)	/* ptrace can change this for a bad syscall */
 	movq %rsp,%rdi        /* &pt_regs -> arg1 */
 	call syscall_trace_enter
@@ -425,6 +433,8 @@ ia32_do_call:
 	call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
 ia32_sysret:
 	movq %rax,RAX-ARGOFFSET(%rsp)
+ia32_ret_from_sys_call:
+	CLEAR_RREGS -ARGOFFSET
 	jmp int_ret_from_sys_call 
 
 ia32_tracesys:			 
@@ -442,8 +452,8 @@ END(ia32_syscall)
 
 ia32_badsys:
 	movq $0,ORIG_RAX-ARGOFFSET(%rsp)
-	movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
-	jmp int_ret_from_sys_call
+	movq $-ENOSYS,%rax
+	jmp ia32_sysret
 
 quiet_ni_syscall:
 	movq $-ENOSYS,%rax
diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h
index 5d367caa0e3..549860d3be8 100644
--- a/arch/x86/include/asm/cache.h
+++ b/arch/x86/include/asm/cache.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_CACHE_H
 #define _ASM_X86_CACHE_H
 
+#include <linux/linkage.h>
+
 /* L1 cache line size */
 #define L1_CACHE_SHIFT	(CONFIG_X86_L1_CACHE_SHIFT)
 #define L1_CACHE_BYTES	(1 << L1_CACHE_SHIFT)
@@ -13,7 +15,7 @@
 #ifdef CONFIG_SMP
 #define __cacheline_aligned_in_smp					\
 	__attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT))))	\
-	__attribute__((__section__(".data.page_aligned")))
+	__page_aligned_data
 #endif
 #endif
 
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index 7c5ef8b14d9..46fc474fd81 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -161,7 +161,8 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	    "adcl $0, %0	;\n"
 	    : "=&r" (sum)
 	    : "r" (saddr), "r" (daddr),
-	      "r" (htonl(len)), "r" (htonl(proto)), "0" (sum));
+	      "r" (htonl(len)), "r" (htonl(proto)), "0" (sum)
+	    : "memory");
 
 	return csum_fold(sum);
 }
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 82ceb788a98..ee1931be659 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -312,19 +312,23 @@ static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
 
 extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64);
 
-#define cmpxchg64(ptr, o, n)						\
-({									\
-	__typeof__(*(ptr)) __ret;					\
-	if (likely(boot_cpu_data.x86 > 4))				\
-		__ret = (__typeof__(*(ptr)))__cmpxchg64((ptr),		\
-				(unsigned long long)(o),		\
-				(unsigned long long)(n));		\
-	else								\
-		__ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr),	\
-				(unsigned long long)(o),		\
-				(unsigned long long)(n));		\
-	__ret;								\
-})
+#define cmpxchg64(ptr, o, n)					\
+({								\
+	__typeof__(*(ptr)) __ret;				\
+	__typeof__(*(ptr)) __old = (o);				\
+	__typeof__(*(ptr)) __new = (n);				\
+	alternative_io("call cmpxchg8b_emu",			\
+			"lock; cmpxchg8b (%%esi)" ,		\
+		       X86_FEATURE_CX8,				\
+		       "=A" (__ret),				\
+		       "S" ((ptr)), "0" (__old),		\
+		       "b" ((unsigned int)__new),		\
+		       "c" ((unsigned int)(__new>>32))		\
+		       : "memory");				\
+	__ret; })
+
+
+
 #define cmpxchg64_local(ptr, o, n)					\
 ({									\
 	__typeof__(*(ptr)) __ret;					\
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3be000435fa..d83892226f7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -796,6 +796,7 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index b608a64c581..f1363b72364 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -133,6 +133,8 @@ static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
 static inline void enable_p5_mce(void) {}
 #endif
 
+extern void (*x86_mce_decode_callback)(struct mce *m);
+
 void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
 DECLARE_PER_CPU(struct sys_device, mce_dev);
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index f923203dc39..4a2d4e0c18d 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -37,12 +37,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 
 	if (likely(prev != next)) {
 		/* stop flush ipis for the previous mm */
-		cpu_clear(cpu, prev->cpu_vm_mask);
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
 #ifdef CONFIG_SMP
 		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		percpu_write(cpu_tlbstate.active_mm, next);
 #endif
-		cpu_set(cpu, next->cpu_vm_mask);
+		cpumask_set_cpu(cpu, mm_cpumask(next));
 
 		/* Re-load page tables */
 		load_cr3(next->pgd);
@@ -58,7 +58,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next);
 
-		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
+		if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
 			/* We were in lazy tlb mode and leave_mm disabled
 			 * tlb flush IPI delivery. We must reload CR3
 			 * to make sure to use no freed page tables.
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index e63cf7d441e..139d4c1a33a 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -40,8 +40,7 @@ extern unsigned int nmi_watchdog;
 #define NMI_INVALID	3
 
 struct ctl_table;
-struct file;
-extern int proc_nmi_enabled(struct ctl_table *, int , struct file *,
+extern int proc_nmi_enabled(struct ctl_table *, int ,
 			void __user *, size_t *, loff_t *);
 extern int unknown_nmi_panic;
 
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 8aebcc41041..efb38994859 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -840,42 +840,22 @@ static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
 
 static inline unsigned long __raw_local_save_flags(void)
 {
-	unsigned long f;
-
-	asm volatile(paravirt_alt(PARAVIRT_CALL)
-		     : "=a"(f)
-		     : paravirt_type(pv_irq_ops.save_fl),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "cc");
-	return f;
+	return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl);
 }
 
 static inline void raw_local_irq_restore(unsigned long f)
 {
-	asm volatile(paravirt_alt(PARAVIRT_CALL)
-		     : "=a"(f)
-		     : PV_FLAGS_ARG(f),
-		       paravirt_type(pv_irq_ops.restore_fl),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "cc");
+	PVOP_VCALLEE1(pv_irq_ops.restore_fl, f);
 }
 
 static inline void raw_local_irq_disable(void)
 {
-	asm volatile(paravirt_alt(PARAVIRT_CALL)
-		     :
-		     : paravirt_type(pv_irq_ops.irq_disable),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "eax", "cc");
+	PVOP_VCALLEE0(pv_irq_ops.irq_disable);
 }
 
 static inline void raw_local_irq_enable(void)
 {
-	asm volatile(paravirt_alt(PARAVIRT_CALL)
-		     :
-		     : paravirt_type(pv_irq_ops.irq_enable),