Merge branch 'tracing/urgent' into tracing/core

Merge reason: Pick up fixes and move base from -rc1 to -rc5.

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

30 files changed, 246 insertions, 122 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8da93745c087..07e01149e3bf 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
 
@@ -495,7 +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---
@@ -504,6 +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 527519b8a9f9..f2824fb8c79c 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/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 585edebe12cf..49c552c060e9 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -82,7 +82,7 @@ static int aes_set_key_common(struct crypto_tfm *tfm, void *raw_ctx,
 		return -EINVAL;
 	}
 
-	if (irq_fpu_usable())
+	if (!irq_fpu_usable())
 		err = crypto_aes_expand_key(ctx, in_key, key_len);
 	else {
 		kernel_fpu_begin();
@@ -103,7 +103,7 @@ static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));
 
-	if (irq_fpu_usable())
+	if (!irq_fpu_usable())
 		crypto_aes_encrypt_x86(ctx, dst, src);
 	else {
 		kernel_fpu_begin();
@@ -116,7 +116,7 @@ static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));
 
-	if (irq_fpu_usable())
+	if (!irq_fpu_usable())
 		crypto_aes_decrypt_x86(ctx, dst, src);
 	else {
 		kernel_fpu_begin();
@@ -342,7 +342,7 @@ static int ablk_encrypt(struct ablkcipher_request *req)
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 
-	if (irq_fpu_usable()) {
+	if (!irq_fpu_usable()) {
 		struct ablkcipher_request *cryptd_req =
 			ablkcipher_request_ctx(req);
 		memcpy(cryptd_req, req, sizeof(*req));
@@ -363,7 +363,7 @@ static int ablk_decrypt(struct ablkcipher_request *req)
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 
-	if (irq_fpu_usable()) {
+	if (!irq_fpu_usable()) {
 		struct ablkcipher_request *cryptd_req =
 			ablkcipher_request_ctx(req);
 		memcpy(cryptd_req, req, sizeof(*req));
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 74619c4f9fda..1733f9f65e82 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/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3be000435fad..d83892226f73 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 b608a64c5814..f1363b72364f 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/paravirt.h b/arch/x86/include/asm/paravirt.h
index 8aebcc41041d..efb38994859c 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),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "eax", "cc");
+	PVOP_VCALLEE0(pv_irq_ops.irq_enable);
 }
 
 static inline unsigned long __raw_local_irq_save(void)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index dd0f5b32489d..9357473c8da0 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -494,10 +494,11 @@ int paravirt_disable_iospace(void);
 #define EXTRA_CLOBBERS
 #define VEXTRA_CLOBBERS
 #else  /* CONFIG_X86_64 */
+/* [re]ax isn't an arg, but the return val */
 #define PVOP_VCALL_ARGS					\
 	unsigned long __edi = __edi, __esi = __esi,	\
-		__edx = __edx, __ecx = __ecx
-#define PVOP_CALL_ARGS		PVOP_VCALL_ARGS, __eax
+		__edx = __edx, __ecx = __ecx, __eax = __eax
+#define PVOP_CALL_ARGS		PVOP_VCALL_ARGS
 
 #define PVOP_CALL_ARG1(x)		"D" ((unsigned long)(x))
 #define PVOP_CALL_ARG2(x)		"S" ((unsigned long)(x))
@@ -509,6 +510,7 @@ int paravirt_disable_iospace(void);
 				"=c" (__ecx)
 #define PVOP_CALL_CLOBBERS	PVOP_VCALL_CLOBBERS, "=a" (__eax)
 
+/* void functions are still allowed [re]ax for scratch */
 #define PVOP_VCALLEE_CLOBBERS	"=a" (__eax)
 #define PVOP_CALLEE_CLOBBERS	PVOP_VCALLEE_CLOBBERS
 
@@ -583,8 +585,8 @@ int paravirt_disable_iospace(void);
 		       VEXTRA_CLOBBERS,					\
 		       pre, post, ##__VA_ARGS__)
 
-#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...)			\
-	____PVOP_CALL(rettype, op.func, CLBR_RET_REG,			\
+#define __PVOP_VCALLEESAVE(op, pre, post, ...)				\
+	____PVOP_VCALL(op.func, CLBR_RET_REG,				\
 		      PVOP_VCALLEE_CLOBBERS, ,				\
 		      pre, post, ##__VA_ARGS__)
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 183c3457d2f4..b1598a9436d0 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -85,6 +85,18 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_wait);
 static DEFINE_PER_CPU(struct mce, mces_seen);
 static int			cpu_missing;
 
+static void default_decode_mce(struct mce *m)
+{
+	pr_emerg("No human readable MCE decoding support on this CPU type.\n");
+	pr_emerg("Run the message through 'mcelog --ascii' to decode.\n");
+}
+
+/*
+ * CPU/chipset specific EDAC code can register a callback here to print
+ * MCE errors in a human-readable form:
+ */
+void (*x86_mce_decode_callback)(struct mce *m) = default_decode_mce;
+EXPORT_SYMBOL(x86_mce_decode_callback);
 
 /* MCA banks polled by the period polling timer for corrected events */
 DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
@@ -165,46 +177,46 @@ void mce_log(struct mce *mce)
 	set_bit(0, &mce_need_notify);
 }
 
-void __weak decode_mce(struct mce *m)
-{
-	return;
-}
-
 static void print_mce(struct mce *m)
 {
-	printk(KERN_EMERG
-	       "CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n",
+	pr_emerg("CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n",
 	       m->extcpu, m->mcgstatus, m->bank, m->status);
+
 	if (m->ip) {
-		printk(KERN_EMERG "RIP%s %02x:<%016Lx> ",
-		       !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
-		       m->cs, m->ip);
+		pr_emerg("RIP%s %02x:<%016Lx> ",
+			!(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
+				m->cs, m->ip);
+
 		if (m->cs == __KERNEL_CS)
 			print_symbol("{%s}", m->ip);
-		printk(KERN_CONT "\n");
+		pr_cont("\n");
 	}
-	printk(KERN_EMERG "TSC %llx ", m->tsc);
+
+	pr_emerg("TSC %llx ", m->tsc);
 	if (m->addr)
-		printk(KERN_CONT "ADDR %llx ", m->addr);
+		pr_cont("ADDR %llx ", m->addr);
 	if (m->misc)
-		printk(KERN_CONT "MISC %llx ", m->misc);
-	printk(KERN_CONT "\n");
-	printk(KERN_EMERG "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
-			m->cpuvendor, m->cpuid, m->time, m->socketid,
-			m->apicid);
+		pr_cont("MISC %llx ", m->misc);
+
+	pr_cont("\n");
+	pr_emerg("PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
+		m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid);
 
-	decode_mce(m);
+	/*
+	 * Print out human-readable details about the MCE error,
+	 * (if the CPU has an implementation for that):
+	 */
+	x86_mce_decode_callback(m);
 }
 
 static void print_mce_head(void)
 {
-	printk(KERN_EMERG "\nHARDWARE ERROR\n");
+	pr_emerg("\nHARDWARE ERROR\n");
 }
 
 static void print_mce_tail(void)
 {
-	printk(KERN_EMERG "This is not a software problem!\n"
-	       "Run through mcelog --ascii to decode and contact your hardware vendor\n");
+	pr_emerg("This is not a software problem!\n");
 }
 
 #define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -218,6 +230,7 @@ static atomic_t mce_fake_paniced;
 static void wait_for_panic(void)
 {
 	long timeout = PANIC_TIMEOUT*USEC_PER_SEC;
+
 	preempt_disable();
 	local_irq_enable();
 	while (timeout-- > 0)
@@ -285,6 +298,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
 static int msr_to_offset(u32 msr)
 {
 	unsigned bank = __get_cpu_var(injectm.bank);
+
 	if (msr == rip_msr)
 		return offsetof(struct mce, ip);
 	if (msr == MSR_IA32_MCx_STATUS(bank))
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 889f665fe93d..7c785634af2b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/percpu.h>
+#include <linux/sched.h>
 #include <asm/apic.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index f04e72527604..3c1b12d461d1 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -96,17 +96,24 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
 	unsigned long long base, size;
 	char *ptr;
 	char line[LINE_SIZE];
+	int length;
 	size_t linelen;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	if (!len)
-		return -EINVAL;
 
 	memset(line, 0, LINE_SIZE);
-	if (len > LINE_SIZE)
-		len = LINE_SIZE;
-	if (copy_from_user(line, buf, len - 1))
+
+	length = len;
+	length--;
+
+	if (length > LINE_SIZE - 1)
+		length = LINE_SIZE - 1;
+
+	if (length < 0)
+		return -EINVAL;
+
+	if (copy_from_user(line, buf, length))
 		return -EFAULT;
 
 	linelen = strlen(line);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 85419bb7d4ab..d17d482a04f4 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1378,8 +1378,8 @@ static unsigned long ram_alignment(resource_size_t pos)
 	if (mb < 16)
 		return 1024*1024;
 
-	/* To 32MB for anything above that */
-	return 32*1024*1024;
+	/* To 64MB for anything above that */
+	return 64*1024*1024;
 }
 
 #define MAX_RESOURCE_SIZE ((resource_size_t)-1)
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 41fd965c80c6..b9c830c12b4a 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -206,8 +206,11 @@ static int __init setup_early_printk(char *buf)
 
 	while (*buf != '\0') {
 		if (!strncmp(buf, "serial", 6)) {
-			early_serial_init(buf + 6);
+			buf += 6;
+			early_serial_init(buf);
 			early_console_register(&early_serial_console, keep);
+			if (!strncmp(buf, ",ttyS", 5))
+				buf += 5;
 		}
 		if (!strncmp(buf, "ttyS", 4)) {
 			early_serial_init(buf + 4);
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 1736c5a725aa..9c3bd4a2050e 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -15,8 +15,10 @@ EXPORT_SYMBOL(mcount);
  * the export, but dont use it from C code, it is used
  * by assembly code and is not using C calling convention!
  */
+#ifndef CONFIG_X86_CMPXCHG64
 extern void cmpxchg8b_emu(void);
 EXPORT_SYMBOL(cmpxchg8b_emu);
+#endif
 
 /* Networking helper routines. */
 EXPORT_SYMBOL(csum_partial_copy_generic);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 74656d1d4e30..04bbd5278568 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -63,10 +63,10 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count);
 	seq_printf(p, "  Spurious interrupts\n");
-	seq_printf(p, "%*s: ", prec, "CNT");
+	seq_printf(p, "%*s: ", prec, "PMI");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
-	seq_printf(p, "  Performance counter interrupts\n");
+	seq_printf(p, "  Performance monitoring interrupts\n");
 	seq_printf(p, "%*s: ", prec, "PND");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->apic_pending_irqs);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 64b838eac18c..b2a71dca5642 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -35,7 +35,7 @@ int iommu_detected __read_mostly = 0;
 
 /*
  * This variable becomes 1 if iommu=pt is passed on the kernel command line.
- * If this variable is 1, IOMMU implementations do no DMA ranslation for
+ * If this variable is 1, IOMMU implementations do no DMA translation for
  * devices and allow every device to access to whole physical memory. This is
  * useful if a user want to use an IOMMU only for KVM device assignment to
  * guests and not for driver dma translation.
@@ -311,7 +311,7 @@ void pci_iommu_shutdown(void)
 	amd_iommu_shutdown();
 }
 /* Must execute after PCI subsystem */
-fs_initcall(pci_iommu_init);
+rootfs_initcall(pci_iommu_init);
 
 #ifdef CONFIG_PCI
 /* Many VIA bridges seem to corrupt data for DAC. Disable it here */
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 98a827ee9ed7..a7f1b64f86e0 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -16,6 +16,7 @@
 #include <linux/agp_backend.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/pci.h>
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 27349f92a6d7..a1a3cdda06e1 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -4,6 +4,7 @@
 #include <linux/pm.h>
 #include <linux/efi.h>
 #include <linux/dmi.h>
+#include <linux/sched.h>
 #include <linux/tboot.h>
 #include <acpi/reboot.h>
 #include <asm/io.h>
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index dcb00d278512..be2573448ed9 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -38,7 +38,8 @@ unsigned long profile_pc(struct pt_regs *regs)
 #ifdef CONFIG_FRAME_POINTER
 		return *(unsigned long *)(regs->bp + sizeof(long));
 #else
-		unsigned long *sp = (unsigned long *)regs->sp;
+		unsigned long *sp =
+			(unsigned long *)kernel_stack_pointer(regs);
 		/*
 		 * Return address is either directly at stack pointer
 		 * or above a saved flags. Eflags has bits 22-31 zero,
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index 699f7eeb896a..cd022121cab6 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -3,8 +3,16 @@
 #include <asm/trampoline.h>
 #include <asm/e820.h>
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP)
+#define __trampinit
+#define __trampinitdata
+#else
+#define __trampinit __cpuinit
+#define __trampinitdata __cpuinitdata
+#endif
+
 /* ready for x86_64 and x86 */
-unsigned char *__cpuinitdata trampoline_base = __va(TRAMPOLINE_BASE);
+unsigned char *__trampinitdata trampoline_base = __va(TRAMPOLINE_BASE);
 
 void __init reserve_trampoline_memory(void)
 {
@@ -26,7 +34,7 @@ void __init reserve_trampoline_memory(void)
  * bootstrap into the page concerned. The caller
  * has made sure it's suitably aligned.
  */
-unsigned long __cpuinit setup_trampoline(void)
+unsigned long __trampinit setup_trampoline(void)
 {
 	memcpy(trampoline_base, trampoline_data, TRAMPOLINE_SIZE);
 	return virt_to_phys(trampoline_base);
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S
index 596d54c660a5..3af2dff58b21 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/kernel/trampoline_64.S
@@ -32,8 +32,12 @@
 #include <asm/segment.h>
 #include <asm/processor-flags.h>
 
+#ifdef CONFIG_ACPI_SLEEP
+.section .rodata, "a", @progbits
+#else
 /* We can free up the trampoline after bootup if cpu hotplug is not supported. */
 __CPUINITRODATA
+#endif
 .code16
 
 ENTRY(trampoline_data)
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 31e6f6cfe53e..d430e4c30193 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -648,7 +648,7 @@ static inline int __init activate_vmi(void)
 
 	pv_info.paravirt_enabled = 1;
 	pv_info.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK;
-	pv_info.name = "vmi";
+	pv_info.name = "vmi [deprecated]";
 
 	pv_init_ops.patch = vmi_patch;
 
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 82ad523b4901..144e7f60b5e2 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -116,7 +116,7 @@ static s64 __kpit_elapsed(struct kvm *kvm)
 	 * itself with the initial count and continues counting
 	 * from there.
 	 */
-	remaining = hrtimer_expires_remaining(&ps->pit_timer.timer);
+	remaining = hrtimer_get_remaining(&ps->pit_timer.timer);
 	elapsed = ps->pit_timer.period - ktime_to_ns(remaining);
 	elapsed = mod_64(elapsed, ps->pit_timer.period);
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 1ae5ceba7eb2..23c217692ea9 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -521,7 +521,7 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
 	if (apic_get_reg(apic, APIC_TMICT) == 0)
 		return 0;
 
-	remaining = hrtimer_expires_remaining(&apic->lapic_timer.timer);
+	remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
 	if (ktime_to_ns(remaining) < 0)
 		remaining = ktime_set(0, 0);
 
@@ -664,7 +664,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 {
 	ktime_t now = apic->lapic_timer.timer.base->get_time();
 
-	apic->lapic_timer.period = apic_get_reg(apic, APIC_TMICT) *
+	apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT) *
 		    APIC_BUS_CYCLE_NS * apic->divide_count;
 	atomic_set(&apic->lapic_timer.pending, 0);
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index eca41ae9f453..818b92ad82cf 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -156,6 +156,8 @@ module_param(oos_shadow, bool, 0644);
 #define CREATE_TRACE_POINTS
 #include "mmutrace.h"
 
+#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
+
 #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
 
 struct kvm_rmap_desc {
@@ -634,9 +636,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
 	if (*spte & shadow_accessed_mask)
 		kvm_set_pfn_accessed(pfn);
 	if (is_writeble_pte(*spte))
-		kvm_release_pfn_dirty(pfn);
-	else
-		kvm_release_pfn_clean(pfn);
+		kvm_set_pfn_dirty(pfn);
 	rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], sp->role.level);
 	if (!*rmapp) {
 		printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte);
@@ -748,7 +748,8 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn)
 	return write_protected;
 }
 
-static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp)
+static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
+			   unsigned long data)
 {
 	u64 *spte;
 	int need_tlb_flush = 0;
@@ -763,8 +764,47 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp)
 	return need_tlb_flush;
 }
 
+static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
+			     unsigned long data)
+{
+	int need_flush = 0;
+	u64 *spte, new_spte;
+	pte_t *ptep = (pte_t *)data;
+	pfn_t new_pfn;
+
+	WARN_ON(pte_huge(*ptep));
+	new_pfn = pte_pfn(*ptep);
+	spte = rmap_next(kvm, rmapp, NULL);
+	while (spte) {
+		BUG_ON(!is_shadow_present_pte(*spte));
+		rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte);
+		need_flush = 1;
+		if (pte_write(*ptep)) {
+			rmap_remove(kvm, spte);
+			__set_spte(spte, shadow_trap_nonpresent_pte);
+			spte = rmap_next(kvm, rmapp, NULL);
+		} else {
+			new_spte = *spte &~ (PT64_BASE_ADDR_MASK);
+			new_spte |= (u64)new_pfn << PAGE_SHIFT;
+
+			new_spte &= ~PT_WRITABLE_MASK;
+			new_spte &= ~SPTE_HOST_WRITEABLE;
+			if (is_writeble_pte(*spte))
+				kvm_set_pfn_dirty(spte_to_pfn(*spte));
+			__set_spte(spte, new_spte);
+			spte = rmap_next(kvm, rmapp, spte);
+		}
+	}
+	if (need_flush)
+		kvm_flush_remote_tlbs(kvm);
+
+	return 0;
+}
+
 static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
-			  int (*handler)(struct kvm *kvm, unsigned long *rmapp))
+			  unsigned long data,
+			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+					 unsigned long data))
 {
 	int i, j;
 	int retval = 0;
@@ -786,13 +826,15 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 		if (hva >= start && hva < end) {
 			gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
 
-			retval |= handler(kvm, &memslot->rmap[gfn_offset]);
+			retval |= handler(kvm, &memslot->rmap[gfn_offset],
+					  data);
 
 			for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) {
 				int idx = gfn_offset;
 				idx /= KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL + j);
 				retval |= handler(kvm,
-					&memslot->lpage_info[j][idx].rmap_pde);
+					&memslot->lpage_info[j][idx].rmap_pde,
+					data);
 			}
 		}
 	}
@@ -802,10 +844,16 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
 {
-	return kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
+	return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp);
 }
 
-static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp)
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+	kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
+}
+
+static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
+			 unsigned long data)
 {
 	u64 *spte;
 	int young = 0;
@@ -841,13 +889,13 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 	gfn = unalias_gfn(vcpu->kvm, gfn);
 	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
 
-	kvm_unmap_rmapp(vcpu->kvm, rmapp);
+	kvm_unmap_rmapp(vcpu->kvm, rmapp, 0);
 	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);
+	return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp);
 }
 
 #ifdef MMU_DEBUG
@@ -1756,7 +1804,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    unsigned pte_access, int user_fault,
 		    int write_fault, int dirty, int level,
 		    gfn_t gfn, pfn_t pfn, bool speculative,
-		    bool can_unsync)
+		    bool can_unsync, bool reset_host_protection)
 {
 	u64 spte;
 	int ret = 0;
@@ -1783,6 +1831,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
 			kvm_is_mmio_pfn(pfn));
 
+	if (reset_host_protection)
+		spte |= SPTE_HOST_WRITEABLE;
+
 	spte |= (u64)pfn << PAGE_SHIFT;
 
 	if ((pte_access & ACC_WRITE_MASK)
@@ -1828,7 +1879,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			 unsigned pt_access, unsigned pte_access,
 			 int user_fault, int write_fault, int dirty,
 			 int *ptwrite, int level, gfn_t gfn,
-			 pfn_t pfn, bool speculative)
+			 pfn_t pfn, bool speculative,
+			 bool reset_host_protection)
 {
 	int was_rmapped = 0;
 	int was_writeble = is_writeble_pte(*sptep);
@@ -1860,7 +1912,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	}
 
 	if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault,
-		      dirty, level, gfn, pfn, speculative, true)) {
+		      dirty, level, gfn, pfn, speculative, true,
+		      reset_host_protection)) {
 		if (write_fault)
 			*ptwrite = 1;
 		kvm_x86_ops->tlb_flush(vcpu);
@@ -1877,8 +1930,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	page_header_update_slot(vcpu->kvm, sptep, gfn);
 	if (!was_rmapped) {
 		rmap_count = rmap_add(vcpu, sptep, gfn);
-		if (!is_rmap_spte(*sptep))
-			kvm_release_pfn_clean(pfn);
+		kvm_release_pfn_clean(pfn);
 		if (rmap_count > RMAP_RECYCLE_THRESHOLD)
 			rmap_recycle(vcpu, sptep, gfn);
 	} else {
@@ -1909,7 +1961,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 		if (iterator.level == level) {
 			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL,
 				     0, write, 1, &pt_write,
-				     level, gfn, pfn, false);
+				     level, gfn, pfn, false, true);
 			++vcpu->stat.pf_fixed;
 			break;
 		}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index d2fec9c12d22..72558f8ff3f5 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -273,9 +273,13 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
 	if (mmu_notifier_retry(vcpu, vcpu->arch.update_pte.mmu_seq))
 		return;
 	kvm_get_pfn(pfn);
+	/*
+	 * we call mmu_set_spte() with reset_host_protection = true beacuse that
+	 * vcpu->arch.update_pte.pfn was fetched from get_user_pages(write = 1).
+	 */
 	mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0,
 		     gpte & PT_DIRTY_MASK, NULL, PT_PAGE_TABLE_LEVEL,
-		     gpte_to_gfn(gpte), pfn, true);
+		     gpte_to_gfn(gpte), pfn, true, true);
 }
 
 /*
@@ -308,7 +312,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 				     user_fault, write_fault,
 				     gw->ptes[gw->level-1] & PT_DIRTY_MASK,
 				     ptwrite, level,
-				     gw->gfn, pfn, false);
+				     gw->gfn, pfn, false, true);
 			break;
 		}
 
@@ -558,6 +562,7 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu,
 static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
 	int i, offset, nr_present;
+	bool reset_host_protection;
 
 	offset = nr_present = 0;
 
@@ -595,9 +600,16 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		nr_present++;
 		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
+		if (!(sp->spt[i] & SPTE_HOST_WRITEABLE)) {
+			pte_access &= ~ACC_WRITE_MASK;
+			reset_host_protection = 0;
+		} else {
+			reset_host_protection = 1;
+		}
 		set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
 			 is_dirty_gpte(gpte), PT_PAGE_TABLE_LEVEL, gfn,
-			 spte_to_pfn(sp->spt[i]), true, false);
+			 spte_to_pfn(sp->spt[i]), true, false,
+			 reset_host_protection);
 	}
 
 	return !nr_present;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 944cc9c04b3c..c17404add91f 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -767,6 +767,8 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		rdtscll(tsc_this);
 		delta = vcpu->arch.host_tsc - tsc_this;
 		svm->vmcb->control.tsc_offset += delta;
+		if (is_nested(svm))
+			svm->nested.hsave->control.tsc_offset += delta;
 		vcpu->cpu = cpu;
 		kvm_migrate_timers(vcpu);
 		svm->asid_generation = 0;
@@ -2057,10 +2059,14 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 
 	switch (ecx) {
 	case MSR_IA32_TSC: {
-		u64 tsc;
+		u64 tsc_offset;
+
+		if (is_nested(svm))
+			tsc_offset = svm->nested.hsave->control.tsc_offset;
+		else
+			tsc_offset = svm->vmcb->control.tsc_offset;
 
-		rdtscll(tsc);
-		*data = svm->vmcb->control.tsc_offset + tsc;
+		*data = tsc_offset + native_read_tsc();
 		break;
 	}
 	case MSR_K6_STAR:
@@ -2146,10 +2152,17 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 
 	switch (ecx) {
 	case MSR_IA32_TSC: {
-		u64 tsc;
+		u64 tsc_offset = data - native_read_tsc();
+		u64 g_tsc_offset = 0;
+
+		if (is_nested(svm)) {
+			g_tsc_offset = svm->vmcb->control.tsc_offset -
+				       svm->nested.hsave->control.tsc_offset;
+			svm->nested.hsave->control.tsc_offset = tsc_offset;
+		}
+
+		svm->vmcb->control.tsc_offset = tsc_offset + g_tsc_offset;
 
-		rdtscll(tsc);
-		svm->vmcb->control.tsc_offset = data - tsc;
 		break;
 	}
 	case MSR_K6_STAR:
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f3812014bd0b..ed53b42caba1 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -709,7 +709,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (vcpu->cpu != cpu) {
 		vcpu_clear(vmx);
 		kvm_migrate_timers(vcpu);
-		vpid_sync_vcpu_all(vmx);
+		set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests);
 		local_irq_disable();
 		list_add(&vmx->local_vcpus_link,
 			 &per_cpu(vcpus_on_cpu, cpu));
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index be451ee44249..9b9695322f56 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1591,6 +1591,8 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 
 	if (cpuid->nent < 1)
 		goto out;
+	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
+		cpuid->nent = KVM_MAX_CPUID_ENTRIES;
 	r = -ENOMEM;
 	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
 	if (!cpuid_entries)
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 3e549b8ec8c9..85f5db95c60f 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -15,8 +15,10 @@ ifeq ($(CONFIG_X86_32),y)
         obj-y += atomic64_32.o
         lib-y += checksum_32.o
         lib-y += strstr_32.o
-        lib-y += semaphore_32.o string_32.o cmpxchg8b_emu.o
-
+        lib-y += semaphore_32.o string_32.o
+ifneq ($(CONFIG_X86_CMPXCHG64),y)
+        lib-y += cmpxchg8b_emu.o
+endif
         lib-$(CONFIG_X86_USE_3DNOW) += mmx_32.o
 else
         obj-y += io_64.o iomap_copy_64.o